2022
Conference article
Open Access
Cultural Heritage 3D data on the Web: issues and perspectives
Potenziani M., Ponchio F., Callieri M., Cignoni P., Scopigno R.
Les modèles numériques 3D sont unanimement considérés comme un atout inestimable pour l'étude, la gestion et la promotion du patrimoine culturel. L'urgence de COVID-19 a accéléré la tendance commune à travailler à distance et, pour le patrimoine culturel, la présentation, le partage et l'accès aux données 3D en ligne sont désormais perçus comme une nécessité. Malheureusement, l'absence de méthodologies, d'outils et d'infrastructures standard rend difficile le passage du stockage local à la gestion en ligne de données 3D complexes. Dans cette contribution, nous souhaitons évaluer l'état de l'art de l'utilisation avancée de la 3D sur le web, en soulignant les besoins actuels, en présentant quelques études de cas et en explorant les perspectives futures.Source: Heritage for the Future, Science for Heritage: A European Adventure for Research and Innovation, pp. 378–383, Paris, France, 15-16/03/2022
Potenziani M., Ponchio F., Callieri M., Cignoni P., Scopigno R.
Les modèles numériques 3D sont unanimement considérés comme un atout inestimable pour l'étude, la gestion et la promotion du patrimoine culturel. L'urgence de COVID-19 a accéléré la tendance commune à travailler à distance et, pour le patrimoine culturel, la présentation, le partage et l'accès aux données 3D en ligne sont désormais perçus comme une nécessité. Malheureusement, l'absence de méthodologies, d'outils et d'infrastructures standard rend difficile le passage du stockage local à la gestion en ligne de données 3D complexes. Dans cette contribution, nous souhaitons évaluer l'état de l'art de l'utilisation avancée de la 3D sur le web, en soulignant les besoins actuels, en présentant quelques études de cas et en explorant les perspectives futures.Source: Heritage for the Future, Science for Heritage: A European Adventure for Research and Innovation, pp. 378–383, Paris, France, 15-16/03/2022
See at:
ISTI Repository 
| www.heritageresearch-hub.eu | CNR ExploRA
2021
Journal article
Open Access
Smart Working at CNR-ISTI in the COVID-19 Era
Scopigno R., Giorgi D.
The CNR Institute for Information Science and Technologies describes its experience in adapting to smart working, which has dramatically changed the institute's modus operandi for most of the year 2020.Source: ERCIM news (2021): 6–7.
Scopigno R., Giorgi D.
The CNR Institute for Information Science and Technologies describes its experience in adapting to smart working, which has dramatically changed the institute's modus operandi for most of the year 2020.Source: ERCIM news (2021): 6–7.
See at:
ercim-news.ercim.eu | ISTI Repository | CNR ExploRA
2021
Contribution to book
Restricted
Virtual clones for cultural heritage applications
Potenziani M., Banterle F., Callieri M., Dellepiane M., Ponchio F., Scopigno R.
Digital technologies are now mature for producing high quality digital replicas of Cultural Heritage (CH) artifacts. The research results produced in the last decade have shown an impressive evolution and consolidation of the technologies for acquiring high-quality digital 3D models, encompassing both geometry and color (or, better, surface reflectance properties). Some recent technologies for constructing 3D models enriched by a high-quality encoding of the color attribute will be presented. The focus of this paper is to show and discuss practical solutions, which could be deployed without requiring the installation of a specific or sophisticated acquisition lab setup. In the second part of this paper, we focus on new solutions for the interactive visualization of complex models, adequate for modern communication channels such as the web and the mobile platforms. Together with the algorithms and approaches, we show also some practical examples where high-quality 3D models have been used in CH research, restoration and conservation.Source: From Pen to Pixel - Studies of the Roman Forum and the Digital Future of World Heritage, edited by Fortini Patrizia, Krusche Krupali, pp. 225–233. Roma: L'Erma di Bretschneider, 2021
Potenziani M., Banterle F., Callieri M., Dellepiane M., Ponchio F., Scopigno R.
Digital technologies are now mature for producing high quality digital replicas of Cultural Heritage (CH) artifacts. The research results produced in the last decade have shown an impressive evolution and consolidation of the technologies for acquiring high-quality digital 3D models, encompassing both geometry and color (or, better, surface reflectance properties). Some recent technologies for constructing 3D models enriched by a high-quality encoding of the color attribute will be presented. The focus of this paper is to show and discuss practical solutions, which could be deployed without requiring the installation of a specific or sophisticated acquisition lab setup. In the second part of this paper, we focus on new solutions for the interactive visualization of complex models, adequate for modern communication channels such as the web and the mobile platforms. Together with the algorithms and approaches, we show also some practical examples where high-quality 3D models have been used in CH research, restoration and conservation.Source: From Pen to Pixel - Studies of the Roman Forum and the Digital Future of World Heritage, edited by Fortini Patrizia, Krusche Krupali, pp. 225–233. Roma: L'Erma di Bretschneider, 2021
See at:
www.lerma.it 
| CNR ExploRA
2021
Conference article
Open Access
Mixing visual media for cultural heritage
Scopigno R.
The Cultural Heritage (CH) domain is a field where many different visual media are constituent elements of the main activities: study, conservation, dissemination, and presentation to the public (museum visitors, tourists, practitioners). Those media are usually used in isolation, adopting specific visualization tools. This paper aims to present several experiences where multiple visual media have been used in a coordinated manner by fusing or presenting them in the same visualization context. These approaches experimented with new interaction and visualization methodologies to use different media in a synergic way. CH domain is an ideal field of experimentation of the potential of media integration/fusion/ cross-analysis. According to our understanding, using multiple media can improve insight capability. We guide the reader in the analysis of some pioneering experiences and approaches and try to deduce, for each of them, the potential improvement granted in terms of data communication or analysis. A final discussion tries to highlight the work needed for a wider acceptance and increased impact of those approaches.Source: RISE IMET 2021: International Conference on Emerging Technologies and the Digital Transformation of Museums and Heritage Sites, pp. 297–315, Nicosia, Cyprus, June 2-4, 2021
DOI: 10.1007/978-3-030-83647-4_20
Project(s): EVOCATION
Metrics:
Scopigno R.
The Cultural Heritage (CH) domain is a field where many different visual media are constituent elements of the main activities: study, conservation, dissemination, and presentation to the public (museum visitors, tourists, practitioners). Those media are usually used in isolation, adopting specific visualization tools. This paper aims to present several experiences where multiple visual media have been used in a coordinated manner by fusing or presenting them in the same visualization context. These approaches experimented with new interaction and visualization methodologies to use different media in a synergic way. CH domain is an ideal field of experimentation of the potential of media integration/fusion/ cross-analysis. According to our understanding, using multiple media can improve insight capability. We guide the reader in the analysis of some pioneering experiences and approaches and try to deduce, for each of them, the potential improvement granted in terms of data communication or analysis. A final discussion tries to highlight the work needed for a wider acceptance and increased impact of those approaches.Source: RISE IMET 2021: International Conference on Emerging Technologies and the Digital Transformation of Museums and Heritage Sites, pp. 297–315, Nicosia, Cyprus, June 2-4, 2021
DOI: 10.1007/978-3-030-83647-4_20
Project(s): EVOCATION
Metrics:
See at:
ISTI Repository | link.springer.com | CNR ExploRA
2021
Journal article
Open Access
"Ecce Homo" by Antonello da Messina, from non-invasive investigations to data fusion and dissemination
Albertin F., Ruberto C., Cucci C., Callieri M., Potenziani M., Siotto E., Pingi P., Scopigno R., Bettuzzi M., Brancaccio R., Morigi M. P., Castelli L., Taccetti F., Picollo M., Stefani L., De Vita F.
Scientific investigations of artworks are crucial in terms of preservation since they provide a measurable evaluation of the materials and the state of conservation. This is the case of Antonello da Messina's painting "Ecce Homo": its delicate state of conservation, with the need for constant monitoring, required a broad and in-depth diagnostic campaign to support the restorers. The project was carried out entirely in situ using non-invasive cutting-edge techniques and proposes a multimodal and data-centric approach, integrating 3D and 2D methodologies. The surface irregularities and the support were analysed with a structured-light 3D scanner and X-ray tomography. The painting materials were investigated with X-ray fluorescence scanning (MA-XRF) and reflectance hyperspectral imaging (HSI). Primarily, the data were jointly used for a scientific scope and provided new knowledge of the painting in terms of materials and painting techniques. In addition, two web-based interactive platforms were developed: one to provide restorers and experts with a new perspective of the hidden geometries of the painting, and the other targeted at the general public for dissemination purposes. The results of the Ecce Homo scientific analysis were exhibited, using a touch-screen interface, and developed for different user levels, from adults to kids.Source: Scientific reports (Nature Publishing Group) 11 (2021): 15868–15885. doi:10.1038/s41598-021-95212-2
DOI: 10.1038/s41598-021-95212-2
Project(s): E-RIHS PP
Metrics:
Albertin F., Ruberto C., Cucci C., Callieri M., Potenziani M., Siotto E., Pingi P., Scopigno R., Bettuzzi M., Brancaccio R., Morigi M. P., Castelli L., Taccetti F., Picollo M., Stefani L., De Vita F.
Scientific investigations of artworks are crucial in terms of preservation since they provide a measurable evaluation of the materials and the state of conservation. This is the case of Antonello da Messina's painting "Ecce Homo": its delicate state of conservation, with the need for constant monitoring, required a broad and in-depth diagnostic campaign to support the restorers. The project was carried out entirely in situ using non-invasive cutting-edge techniques and proposes a multimodal and data-centric approach, integrating 3D and 2D methodologies. The surface irregularities and the support were analysed with a structured-light 3D scanner and X-ray tomography. The painting materials were investigated with X-ray fluorescence scanning (MA-XRF) and reflectance hyperspectral imaging (HSI). Primarily, the data were jointly used for a scientific scope and provided new knowledge of the painting in terms of materials and painting techniques. In addition, two web-based interactive platforms were developed: one to provide restorers and experts with a new perspective of the hidden geometries of the painting, and the other targeted at the general public for dissemination purposes. The results of the Ecce Homo scientific analysis were exhibited, using a touch-screen interface, and developed for different user levels, from adults to kids.Source: Scientific reports (Nature Publishing Group) 11 (2021): 15868–15885. doi:10.1038/s41598-021-95212-2
DOI: 10.1038/s41598-021-95212-2
Project(s): E-RIHS PP
Metrics:
See at:
Scientific Reports | Scientific Reports | ISTI Repository | Scientific Reports | Scientific Reports | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna | CNR ExploRA
2021
Contribution to book
Unknown
Documentation and analysis of the deformations of the panel and painted surface with 3D scanner
Pingi P., Siotto E., Palma G., Scopigno R.
Despite what might be assumed, the surface of a painting on a canvas or a wooden panel is not perfectly flat, but rather is characterized by a complex three-dimensionality. The paint the artist lays down on the support possesses its own body and thickness, that, even on a millimeter or sub-millimeter scale, may be detected using instruments and three-dimensional measurement applications. At the same time, a wooden panel may be affected by deformations from historical or restoration changes, which may be readily revealed and documented. When analyzing a work of art subjected to an important restoration treatment, as was the case of the Adoration of the Magi by Leonardo da Vinci, a precise 3D documentation of the painted surface is thus strictly linked to the state of its wooden support. As is well-known, a panel painting is a layered structure (usually a protective varnish coating, paint layers, usually preparatory or ground layers, and the wooden panel), each with different physical and chemical compositions. Therefore, an accurate geometric 3D acquisition of the board structure and its connecting components (butterfly joins or dowel inserts) and the auxiliary support system (crossbars) may supply information to not only improve understanding of how the painting was made and its condition, but also permit it to be monitored over time or during restoration. Furthermore, the application of modern 3D computer graphics technologies is not only a valid diagnostic aid to acquiring knowledge about the work, but also a way to map information and share it (for example art historical information, technical data, and the results of chemical and physical analyses), making them easily accessible online both to experts in the sector and a wider public, thanks to specifically developed multimedia systems.1 In the case of the unfinished masterpiece by Leonardo, a complete high resolution 3D acquisition was performed in order to show and measure--at the moment during conservation treatment--a map of deviations from planarity caused by the curvature and warp of the wooden boards, permitting the documenting of the spatial deformation of the painted surface and the monitoring of its state of preservation.Source: The restoration of Leonardo da Vinci's Adoration of the Magi - Rediscovering a masterpiece, edited by Ciatti M., Frosinini C., pp. 281–286. Firenze: Edifir - Edizioni Firenze s.r.l., 2021
Pingi P., Siotto E., Palma G., Scopigno R.
Despite what might be assumed, the surface of a painting on a canvas or a wooden panel is not perfectly flat, but rather is characterized by a complex three-dimensionality. The paint the artist lays down on the support possesses its own body and thickness, that, even on a millimeter or sub-millimeter scale, may be detected using instruments and three-dimensional measurement applications. At the same time, a wooden panel may be affected by deformations from historical or restoration changes, which may be readily revealed and documented. When analyzing a work of art subjected to an important restoration treatment, as was the case of the Adoration of the Magi by Leonardo da Vinci, a precise 3D documentation of the painted surface is thus strictly linked to the state of its wooden support. As is well-known, a panel painting is a layered structure (usually a protective varnish coating, paint layers, usually preparatory or ground layers, and the wooden panel), each with different physical and chemical compositions. Therefore, an accurate geometric 3D acquisition of the board structure and its connecting components (butterfly joins or dowel inserts) and the auxiliary support system (crossbars) may supply information to not only improve understanding of how the painting was made and its condition, but also permit it to be monitored over time or during restoration. Furthermore, the application of modern 3D computer graphics technologies is not only a valid diagnostic aid to acquiring knowledge about the work, but also a way to map information and share it (for example art historical information, technical data, and the results of chemical and physical analyses), making them easily accessible online both to experts in the sector and a wider public, thanks to specifically developed multimedia systems.1 In the case of the unfinished masterpiece by Leonardo, a complete high resolution 3D acquisition was performed in order to show and measure--at the moment during conservation treatment--a map of deviations from planarity caused by the curvature and warp of the wooden boards, permitting the documenting of the spatial deformation of the painted surface and the monitoring of its state of preservation.Source: The restoration of Leonardo da Vinci's Adoration of the Magi - Rediscovering a masterpiece, edited by Ciatti M., Frosinini C., pp. 281–286. Firenze: Edifir - Edizioni Firenze s.r.l., 2021
See at: CNR ExploRA
2020
Journal article
Open Access
Effective annotations over 3D models
Ponchio F., Callieri M., Dellepiane M., Scopigno R.
Annotation support in interactive systems is often considered a simple task by the CG community, since it entails the apparently easy selection of a region and its connection with some information. The reality appears more complex. The scope of this paper is twofold: first, to review the status of this domain, discussing and characterizing several approaches proposed in literature to manage annotations over geometric models; second, to present in detail an innovative solution proposed and assessed in the framework of Cultural Heritage (CH) applications, called ClippingVolumes. At the annotation definition stage ClippingVolumes uses 3D data to characterize the annotation region; subsequently, annotations are visualized by adopting a two-pass rendering solution which uses stencil buffers, thus without introducing new geometric elements, changing the topology or duplicating geometry elements. It solves most of the issues that afflict the current state of the art, such as fragmentation, annotation transfer to multiple representations, and multi-resolution data encoding. The latter is a mandatory requirement to produce efficient web-based systems. We implemented and we fully tested this approach in the framework of a complex system that supports the documentation of CH restoration projects.Source: Computer graphics forum (Online) 39 (2020): 89–105. doi:10.1111/cgf.13664
DOI: 10.1111/cgf.13664
Metrics:
Ponchio F., Callieri M., Dellepiane M., Scopigno R.
Annotation support in interactive systems is often considered a simple task by the CG community, since it entails the apparently easy selection of a region and its connection with some information. The reality appears more complex. The scope of this paper is twofold: first, to review the status of this domain, discussing and characterizing several approaches proposed in literature to manage annotations over geometric models; second, to present in detail an innovative solution proposed and assessed in the framework of Cultural Heritage (CH) applications, called ClippingVolumes. At the annotation definition stage ClippingVolumes uses 3D data to characterize the annotation region; subsequently, annotations are visualized by adopting a two-pass rendering solution which uses stencil buffers, thus without introducing new geometric elements, changing the topology or duplicating geometry elements. It solves most of the issues that afflict the current state of the art, such as fragmentation, annotation transfer to multiple representations, and multi-resolution data encoding. The latter is a mandatory requirement to produce efficient web-based systems. We implemented and we fully tested this approach in the framework of a complex system that supports the documentation of CH restoration projects.Source: Computer graphics forum (Online) 39 (2020): 89–105. doi:10.1111/cgf.13664
DOI: 10.1111/cgf.13664
Metrics:
See at:
ISTI Repository | Computer Graphics Forum | onlinelibrary.wiley.com | CNR ExploRA
2019
Conference article
Restricted
Analisi dei frammenti di Sectilia vitrei dalla Villa romana di Aiano-Torraccia di Chiusi (si) e studio della tecnica d'esecuzione
Cavalieri M., Landi S., Manna D., Giamello M., Fornacelli C., Bracci S., Palma G., Siotto E., Scopigno R.
The consistent amount of sectilia fragments from the late Roman Villa of Aiano (4th-5th century AD)provides important insights on the study of the diffusion of opus sectile during the Late Roman period. The extent of the corpus of glass slabs, in particular, immediately suggests interesting perspectives on both the archaeological and technological issues. Thanks to cooperation between archaeologist, conservators, IT and scientists, an in-depth study of the repertory is in progress to provide important information about the technologies and the raw materials used to produce a number of selected samples. High-resolution images have been obtained via Reflectance Transformation Imaging (RTI) to better understand all the different phases characterizing the manufacture of the more complex slabs. Due to their flexibility and low analytical costs, portable and non-invasive analytical techniques provided a fast and quite accurate definition of the chemical and mineralogical properties of each sample and the first classification of a large number of slabs in compositional clusters. Portable X-Ray Fluorescence (p-XRF) and Fiber Optics Reflectance Spectroscopy (FORS) allowed a first definition of the chemical variability within the repertory and provided indications about both manufacturing and coloring techniques.Source: Atti del XXIV Colloquio dell'associazione italiana per lo Studio e la Conservazione del Mosaico, pp. 605–617, Este, Padova, Italy, 14-17 marzo 2018
Cavalieri M., Landi S., Manna D., Giamello M., Fornacelli C., Bracci S., Palma G., Siotto E., Scopigno R.
The consistent amount of sectilia fragments from the late Roman Villa of Aiano (4th-5th century AD)provides important insights on the study of the diffusion of opus sectile during the Late Roman period. The extent of the corpus of glass slabs, in particular, immediately suggests interesting perspectives on both the archaeological and technological issues. Thanks to cooperation between archaeologist, conservators, IT and scientists, an in-depth study of the repertory is in progress to provide important information about the technologies and the raw materials used to produce a number of selected samples. High-resolution images have been obtained via Reflectance Transformation Imaging (RTI) to better understand all the different phases characterizing the manufacture of the more complex slabs. Due to their flexibility and low analytical costs, portable and non-invasive analytical techniques provided a fast and quite accurate definition of the chemical and mineralogical properties of each sample and the first classification of a large number of slabs in compositional clusters. Portable X-Ray Fluorescence (p-XRF) and Fiber Optics Reflectance Spectroscopy (FORS) allowed a first definition of the chemical variability within the repertory and provided indications about both manufacturing and coloring techniques.Source: Atti del XXIV Colloquio dell'associazione italiana per lo Studio e la Conservazione del Mosaico, pp. 605–617, Este, Padova, Italy, 14-17 marzo 2018
See at:
www.aiscom.it | CNR ExploRA
2019
Report
Open Access
Share -- Publish -- Store -- Preserve. Methodologies, Tools and Challenges for 3D Use in Social Sciences and Humanities (White Paper)
Alaoui M'darhri A., Baillet V., Bourineau B., Calantropio A., Carpentiero G., Chayani Cnrs M., De Luca L., Dudek I., Dutailly Cnrs B., Gautier H., Grilli E., Grimaud V., Hoffmann C., Joffres A., Jon?i? N., Jordan M., Kimball J., Manuel A., Mcinerny P., Muñoz I., Neroulidis A., Nocerino E., Pamart A., Papadopoulos C., Potenziani M., Saubestre E., Scopigno R., Seillier D., Tournon-Valiente S., Trognitz M., Vallet J-M, Zuanni C.
Through this White Paper, which gathers contributions from experts of 3D data as well as professionals concerned with the interoperability and sustainability of 3D research data, the PARTHENOS project aims at highlighting some of the current issues they have to face, with possible specific points according to the discipline, and potential practices and methodologies to deal with these issues. During the workshop, several tools to deal with these issues have been introduced and confronted with the participants' experiences, this White Paper now intends to go further by also integrating participants feedbacks and suggestions of potential improvements. Therefore, even if the focus is put on specific tools, the main goal is to contribute to the development of standardized good practices related to the sharing, publication, storage and long-term preservation of 3D data.Source: ISTI Technical Reports, 2019
Project(s): PARTHENOS
Alaoui M'darhri A., Baillet V., Bourineau B., Calantropio A., Carpentiero G., Chayani Cnrs M., De Luca L., Dudek I., Dutailly Cnrs B., Gautier H., Grilli E., Grimaud V., Hoffmann C., Joffres A., Jon?i? N., Jordan M., Kimball J., Manuel A., Mcinerny P., Muñoz I., Neroulidis A., Nocerino E., Pamart A., Papadopoulos C., Potenziani M., Saubestre E., Scopigno R., Seillier D., Tournon-Valiente S., Trognitz M., Vallet J-M, Zuanni C.
Through this White Paper, which gathers contributions from experts of 3D data as well as professionals concerned with the interoperability and sustainability of 3D research data, the PARTHENOS project aims at highlighting some of the current issues they have to face, with possible specific points according to the discipline, and potential practices and methodologies to deal with these issues. During the workshop, several tools to deal with these issues have been introduced and confronted with the participants' experiences, this White Paper now intends to go further by also integrating participants feedbacks and suggestions of potential improvements. Therefore, even if the focus is put on specific tools, the main goal is to contribute to the development of standardized good practices related to the sharing, publication, storage and long-term preservation of 3D data.Source: ISTI Technical Reports, 2019
Project(s): PARTHENOS
See at:
hal.archives-ouvertes.fr | ISTI Repository | CNR ExploRA
2019
Report
Open Access
SOROS: Sciadro online reconstruction by odometry and stereo-matching
Ganovelli F., Malomo L., Scopigno R.
In this report we show how to interactively create 3D models for scenes seen by a common off-the-shelf smartphone. Our approach combines Visual Odometry with IMU sensors in order to achieve interactive 3D reconstruction of the scene as seen from the camera.Source: ISTI Technical reports, 2019
Ganovelli F., Malomo L., Scopigno R.
In this report we show how to interactively create 3D models for scenes seen by a common off-the-shelf smartphone. Our approach combines Visual Odometry with IMU sensors in order to achieve interactive 3D reconstruction of the scene as seen from the camera.Source: ISTI Technical reports, 2019
See at:
ISTI Repository | CNR ExploRA
2019
Journal article
Open Access
Deformation analysis of Leonardo da Vinci's "Adorazione dei Magi" through temporal unrelated 3D digitization
Palma G., Pingi P., Siotto E., Bellucci R., Guidi G., Scopigno R.
3D scanning is an effective technology for dealing at different levels the state of conservation/deformation of a panel painting, from the micro-geometry of the craquelure to the macro-geometry of the supported used. Unfortunately, the current solutions used to analyze multiple 3D scans acquired over time are based on very controlled acquisition procedures, such as the use of target reference points that are stationary over time and fixed to the artwork, or on complex hardware setups to keep the acquisition device fixed to the artwork. These procedures are challenging when a long monitoring period is involved or during restoration when the painting may be moved several times. This paper presents a new and robust approach to observe and quantify the panel deformations of artworks by comparing 3D models acquired with different scanning devices at different times. The procedure is based on a non-rigid registration algorithm that deforms one 3D model over the other in a controlled way, extracting the real deformation field. We apply the method to the 3D scanning data of the unfinished panel painting "Adorazione dei Magi" by Leonardo da Vinci. The data were acquired in 2002 and 2015. First, we analyze the two 3D models with the classical distance from the ideal flat plane of the painting. Then we study the type of deformation of each plank of the support by fitting a quadric surface. Finally, we compare the models before and after the deformation computed by a non-rigid registration algorithm. This last comparison enables the panel deformation to be separated from the structural changes (e.g. the structural restorations on the back and the missing pieces) of the artwork in a more robust way.Source: Journal of cultural heritage 38 (2019): 174–185. doi:10.1016/j.culher.2018.11.001
DOI: 10.1016/j.culher.2018.11.001
Metrics:
Palma G., Pingi P., Siotto E., Bellucci R., Guidi G., Scopigno R.
3D scanning is an effective technology for dealing at different levels the state of conservation/deformation of a panel painting, from the micro-geometry of the craquelure to the macro-geometry of the supported used. Unfortunately, the current solutions used to analyze multiple 3D scans acquired over time are based on very controlled acquisition procedures, such as the use of target reference points that are stationary over time and fixed to the artwork, or on complex hardware setups to keep the acquisition device fixed to the artwork. These procedures are challenging when a long monitoring period is involved or during restoration when the painting may be moved several times. This paper presents a new and robust approach to observe and quantify the panel deformations of artworks by comparing 3D models acquired with different scanning devices at different times. The procedure is based on a non-rigid registration algorithm that deforms one 3D model over the other in a controlled way, extracting the real deformation field. We apply the method to the 3D scanning data of the unfinished panel painting "Adorazione dei Magi" by Leonardo da Vinci. The data were acquired in 2002 and 2015. First, we analyze the two 3D models with the classical distance from the ideal flat plane of the painting. Then we study the type of deformation of each plank of the support by fitting a quadric surface. Finally, we compare the models before and after the deformation computed by a non-rigid registration algorithm. This last comparison enables the panel deformation to be separated from the structural changes (e.g. the structural restorations on the back and the missing pieces) of the artwork in a more robust way.Source: Journal of cultural heritage 38 (2019): 174–185. doi:10.1016/j.culher.2018.11.001
DOI: 10.1016/j.culher.2018.11.001
Metrics:
See at:
ISTI Repository | Journal of Cultural Heritage | www.sciencedirect.com | CNR ExploRA
2019
Journal article
Open Access
DeepFlash: turning a flash selfie into a studio portrait
Capece N., Banterle F., Cignoni P., Ganovelli F., Scopigno R., Erra U.
We present a method for turning a flash selfie taken with a smartphone into a photograph as if it was taken in a studio setting with uniform lighting. Our method uses a convolutional neural network trained on a set of pairs of photographs acquired in an ad-hoc acquisition campaign. Each pair consists of one photograph of a subject's face taken with the camera flash enabled and another one of the same subject in the same pose illuminated using a photographic studio-lighting setup. We show how our method can amend defects introduced by a close-up camera flash, such as specular highlights, shadows, skin shine, and flattened images.Source: Signal processing. Image communication 77 (2019): 28–39. doi:10.1016/j.image.2019.05.013
DOI: 10.1016/j.image.2019.05.013
DOI: 10.48550/arxiv.1901.04252
Metrics:
Capece N., Banterle F., Cignoni P., Ganovelli F., Scopigno R., Erra U.
We present a method for turning a flash selfie taken with a smartphone into a photograph as if it was taken in a studio setting with uniform lighting. Our method uses a convolutional neural network trained on a set of pairs of photographs acquired in an ad-hoc acquisition campaign. Each pair consists of one photograph of a subject's face taken with the camera flash enabled and another one of the same subject in the same pose illuminated using a photographic studio-lighting setup. We show how our method can amend defects introduced by a close-up camera flash, such as specular highlights, shadows, skin shine, and flattened images.Source: Signal processing. Image communication 77 (2019): 28–39. doi:10.1016/j.image.2019.05.013
DOI: 10.1016/j.image.2019.05.013
DOI: 10.48550/arxiv.1901.04252
Metrics:
See at:
arXiv.org e-Print Archive | Signal Processing Image Communication | ISTI Repository | Signal Processing Image Communication | doi.org | CNR ExploRA
2019
Journal article
Restricted
Semi-automated cleaning of laser scanning campaigns with machine learning
Marais P., Dellepiane M., Cignoni P., Scopigno R.
Terrestrial laser scanning campaigns provide an important means to document the 3D structure of historical sites. Unfortunately, the process of converting the 3D point clouds acquired by the laser scanner into a coherent and accurate 3D model has many stages and is not generally automated. In particular, the initial cleaning stage of the pipeline--in which undesired scene points are deleted--remains largely manual and is usually labour intensive. In this article, we introduce a semi-automated cleaning approach that incrementally trains a random forest (RF) classifier on an initial keep/discard point labelling generated by the user when cleaning the first scan(s). The classifier is then used to predict the labelling of the next scan in the sequence. Before this classification is presented to the user, a denoising post-process, based on the 2D range map representation of the laser scan, is applied. This significantly reduces small isolated point clusters that the user would otherwise have to fix. The user then selects the remaining incorrectly labelled points and these are weighted, based on a confidence estimate, and fed back into the classifier to retrain it for the next scan. Our experiments, across 8 scanning campaigns, show that when the scan campaign is coherent, i.e., it does not contain widely disparate or contradictory data, the classifier yields a keep/discard labelling that typically ranges between 95% and 99%. This is somewhat surprising, given that the data in each class can represent many object types, such as a tree, person, wall, and so on, and that no further effort beyond the point labeling of keep/discard is required of the user. We conducted an informal timing experiment over a 15-scan campaign, which compared the processing time required by our software, without user interaction (point label correction) time, against the time taken by an expert user to completely clean all scans. The expert user required 95mins to complete all cleaning. The average time required by the expert to clean a single scan was 6.3mins. Even with current unoptimized code, our system was able to generate keep/discard labels for all scans, with 98% (average) accuracy, in 75mins. This leaves as much as 20mins for the user input required to relabel the 2% of mispredicted points across the set of scans before the full system time would match the expert's cleaning time.Source: ACM journal on computing and cultural heritage (Print) 12 (2019). doi:10.1145/3292027
DOI: 10.1145/3292027
Metrics:
Marais P., Dellepiane M., Cignoni P., Scopigno R.
Terrestrial laser scanning campaigns provide an important means to document the 3D structure of historical sites. Unfortunately, the process of converting the 3D point clouds acquired by the laser scanner into a coherent and accurate 3D model has many stages and is not generally automated. In particular, the initial cleaning stage of the pipeline--in which undesired scene points are deleted--remains largely manual and is usually labour intensive. In this article, we introduce a semi-automated cleaning approach that incrementally trains a random forest (RF) classifier on an initial keep/discard point labelling generated by the user when cleaning the first scan(s). The classifier is then used to predict the labelling of the next scan in the sequence. Before this classification is presented to the user, a denoising post-process, based on the 2D range map representation of the laser scan, is applied. This significantly reduces small isolated point clusters that the user would otherwise have to fix. The user then selects the remaining incorrectly labelled points and these are weighted, based on a confidence estimate, and fed back into the classifier to retrain it for the next scan. Our experiments, across 8 scanning campaigns, show that when the scan campaign is coherent, i.e., it does not contain widely disparate or contradictory data, the classifier yields a keep/discard labelling that typically ranges between 95% and 99%. This is somewhat surprising, given that the data in each class can represent many object types, such as a tree, person, wall, and so on, and that no further effort beyond the point labeling of keep/discard is required of the user. We conducted an informal timing experiment over a 15-scan campaign, which compared the processing time required by our software, without user interaction (point label correction) time, against the time taken by an expert user to completely clean all scans. The expert user required 95mins to complete all cleaning. The average time required by the expert to clean a single scan was 6.3mins. Even with current unoptimized code, our system was able to generate keep/discard labels for all scans, with 98% (average) accuracy, in 75mins. This leaves as much as 20mins for the user input required to relabel the 2% of mispredicted points across the set of scans before the full system time would match the expert's cleaning time.Source: ACM journal on computing and cultural heritage (Print) 12 (2019). doi:10.1145/3292027
DOI: 10.1145/3292027
Metrics:
See at:
dl.acm.org | Journal on Computing and Cultural Heritage | CNR ExploRA
2019
Journal article
Open Access
Developing the ArchAIDE application: A digital workflow for identifying, organising and sharing archaeological pottery using automated image recognition
Anichini F., Banterle F., Buxeda I Garrigós J., Calleri M., Dershowitz N., Diaz D. L., Evans T., Gattiglia G., Gualandi M. L., Hervas M. A., Itkin B., Madrid I Fernandez M, Miguel Gascón E., Remmy M., Richards J., Scopigno R., Vila L., Wolf L., Wright H., Zallocco M.
Every day, archaeologists are working to discover and tell stories using objects from the past, investing considerable time, effort and funding to identify and characterise individual finds. Pottery is of fundamental importance for the comprehension and dating of archaeological contexts, and for understanding the dynamics of production, trade flows, and social interactions. Today, characterisation and classification of ceramics are carried out manually, through the expertise of specialists and the use of analogue catalogues held in archives and libraries. While not seeking to replace the knowledge and expertise of specialists, the ArchAIDE project (archaide.eu) worked to optimise and economise identification process, developing a new system that streamlines the practice of pottery recognition in archaeology, using the latest automatic image recognition technology. At the same time, ArchAIDE worked to ensure archaeologists remained at the heart of the decision-making process within the identification workflow, and focussed on optimising tasks that were repetitive and time consuming. Specifically, ArchAIDE worked to support the essential classification and interpretation work of archaeologists (during both fieldwork and post-excavation analysis) with an innovative app for tablets and smartphones. This paper summarises the work of this three-year project, funded by the European Union's Horizon 2020 Research and Innovation Programme under grant agreement N.693548, with a consortium of partners which has representing both the academic and industry-led ICT domains, and the academic and development-led archaeology domains. The collaborative work of the archaeological and technical partners created a pipeline where potsherds are photographed, their characteristics compared against a trained neural network, and the results returned with suggested matches from a comparative collection with typical pottery types and characteristics. Once the correct type is identified, all relevant information for that type is linked to the new sherd and stored within a database that can be shared online.Source: Internet archaeology 52 (2019). doi:10.11141/ia.52.7
DOI: 10.11141/ia.52.7
Project(s): ArchAIDE
Metrics:
Anichini F., Banterle F., Buxeda I Garrigós J., Calleri M., Dershowitz N., Diaz D. L., Evans T., Gattiglia G., Gualandi M. L., Hervas M. A., Itkin B., Madrid I Fernandez M, Miguel Gascón E., Remmy M., Richards J., Scopigno R., Vila L., Wolf L., Wright H., Zallocco M.
Every day, archaeologists are working to discover and tell stories using objects from the past, investing considerable time, effort and funding to identify and characterise individual finds. Pottery is of fundamental importance for the comprehension and dating of archaeological contexts, and for understanding the dynamics of production, trade flows, and social interactions. Today, characterisation and classification of ceramics are carried out manually, through the expertise of specialists and the use of analogue catalogues held in archives and libraries. While not seeking to replace the knowledge and expertise of specialists, the ArchAIDE project (archaide.eu) worked to optimise and economise identification process, developing a new system that streamlines the practice of pottery recognition in archaeology, using the latest automatic image recognition technology. At the same time, ArchAIDE worked to ensure archaeologists remained at the heart of the decision-making process within the identification workflow, and focussed on optimising tasks that were repetitive and time consuming. Specifically, ArchAIDE worked to support the essential classification and interpretation work of archaeologists (during both fieldwork and post-excavation analysis) with an innovative app for tablets and smartphones. This paper summarises the work of this three-year project, funded by the European Union's Horizon 2020 Research and Innovation Programme under grant agreement N.693548, with a consortium of partners which has representing both the academic and industry-led ICT domains, and the academic and development-led archaeology domains. The collaborative work of the archaeological and technical partners created a pipeline where potsherds are photographed, their characteristics compared against a trained neural network, and the results returned with suggested matches from a comparative collection with typical pottery types and characteristics. Once the correct type is identified, all relevant information for that type is linked to the new sherd and stored within a database that can be shared online.Source: Internet archaeology 52 (2019). doi:10.11141/ia.52.7
DOI: 10.11141/ia.52.7
Project(s): ArchAIDE
Metrics:
See at:
Internet Archaeology | Diposit Digital de la Universitat de Barcelona | Internet Archaeology | ISTI Repository | CNR ExploRA
2019
Journal article
Open Access
Semantic segmentation of Benthic communities from ortho-mosaic maps
Pavoni G., Corsini M., Callieri M., Palma M., Scopigno R.
Visual sampling techniques represent a valuable resource for a rapid, non-invasive data acquisition for underwater monitoring purposes. Long-term monitoring projects usually requires the collection of large quantities of data, and the visual analysis of a human expert operator remains, in this context, a very time consuming task. It has been estimated that only the 1-2% of the acquired images are later analyzed by scientists (Beijbom et al., 2012). Strategies for the automatic recognition of benthic communities are required to effectively exploit all the information contained in visual data. Supervised learning methods, the most promising classification techniques in this field, are commonly affected by two recurring issues: the wide diversity of marine organism, and the small amount of labeled data. In this work, we discuss the advantages offered by the use of annotated high resolution ortho-mosaics of seabed to classify and segment the investigated specimens, and we suggest several strategies to obtain a considerable per-pixel classification performance although the use of a reduced training dataset composed by a single ortho-mosaic. The proposed methodology can be applied to a large number of different species, making the procedure of marine organism identification an highly adaptable task.Source: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Annals) 42 (2019): 151–158. doi:10.5194/isprs-archives-XLII-2-W10-151-2019
DOI: 10.5194/isprs-archives-xlii-2-w10-151-2019
Project(s): GreenBubbles
Metrics:
Pavoni G., Corsini M., Callieri M., Palma M., Scopigno R.
Visual sampling techniques represent a valuable resource for a rapid, non-invasive data acquisition for underwater monitoring purposes. Long-term monitoring projects usually requires the collection of large quantities of data, and the visual analysis of a human expert operator remains, in this context, a very time consuming task. It has been estimated that only the 1-2% of the acquired images are later analyzed by scientists (Beijbom et al., 2012). Strategies for the automatic recognition of benthic communities are required to effectively exploit all the information contained in visual data. Supervised learning methods, the most promising classification techniques in this field, are commonly affected by two recurring issues: the wide diversity of marine organism, and the small amount of labeled data. In this work, we discuss the advantages offered by the use of annotated high resolution ortho-mosaics of seabed to classify and segment the investigated specimens, and we suggest several strategies to obtain a considerable per-pixel classification performance although the use of a reduced training dataset composed by a single ortho-mosaic. The proposed methodology can be applied to a large number of different species, making the procedure of marine organism identification an highly adaptable task.Source: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Annals) 42 (2019): 151–158. doi:10.5194/isprs-archives-XLII-2-W10-151-2019
DOI: 10.5194/isprs-archives-xlii-2-w10-151-2019
Project(s): GreenBubbles
Metrics:
See at:
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | ISTI Repository | ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | www.int-arch-photogramm-remote-sens-spatial-inf-sci.net | CNR ExploRA
2019
Other
Unknown
Three Armenian Manuscripts from Tuscany
Callieri M., Pingi P., Potenziani M., Ponchio F., Scopigno R.
For the temporary exhibition "Three Armenian Manuscripts from Tuscany", taking palce at the Matenadaran Museum (Jerevan, Armenia) from June 9th 2019 to January 9 2020, The Visual Computing Lab of ISTI-CNR created a multimedia interactive kiosk presenting to the museum visitors the pages of the codices and the rooms of the libraries that preserved the books in their long life. The photographic campaign of the codices and buildings has also been used in the monographic volume "Three Armenian Manuscripts from Tuscany (13th - 14th century)", by Anna Rita Fantoni e Giovanna Rasario. Mandragora, Firenze. 2019. ISBN 978-88-7461-475-2 The Kiosk presents, commented by the texts edited by the experts Anna Rita Fantoni e Giovanna Rasario, high-res 360° panorama images of ther libraries (Biblioteca Medicea Laurenziana and Biblioteca di S. Matteo), high-res images of selected pages of the three codices displayed int he exhibition, and relightable RTI images of the decorated cover of one of the codices and of a parchment page illuminated in gold. The Kiosk is based on web technologies: this makes possible the installation on a stand-alone PC (like in the exhibition) but also a web publishing, linked just above. The generation of RTI, and the web visualization of RTI and multiresolution images is managed by the library Relight, developed by ISTI-CNR.
Callieri M., Pingi P., Potenziani M., Ponchio F., Scopigno R.
For the temporary exhibition "Three Armenian Manuscripts from Tuscany", taking palce at the Matenadaran Museum (Jerevan, Armenia) from June 9th 2019 to January 9 2020, The Visual Computing Lab of ISTI-CNR created a multimedia interactive kiosk presenting to the museum visitors the pages of the codices and the rooms of the libraries that preserved the books in their long life. The photographic campaign of the codices and buildings has also been used in the monographic volume "Three Armenian Manuscripts from Tuscany (13th - 14th century)", by Anna Rita Fantoni e Giovanna Rasario. Mandragora, Firenze. 2019. ISBN 978-88-7461-475-2 The Kiosk presents, commented by the texts edited by the experts Anna Rita Fantoni e Giovanna Rasario, high-res 360° panorama images of ther libraries (Biblioteca Medicea Laurenziana and Biblioteca di S. Matteo), high-res images of selected pages of the three codices displayed int he exhibition, and relightable RTI images of the decorated cover of one of the codices and of a parchment page illuminated in gold. The Kiosk is based on web technologies: this makes possible the installation on a stand-alone PC (like in the exhibition) but also a web publishing, linked just above. The generation of RTI, and the web visualization of RTI and multiresolution images is managed by the library Relight, developed by ISTI-CNR.
See at: CNR ExploRA | vcg.isti.cnr.it
2019
Contribution to book
Unknown
Rilievo 3D di Alchimia, ed uso dei modelli 3D per studio e divulgazione
Callieri M., Dellepiane M., Lureau A., Pavoni G., Pingi P., Potenziani M., Scopigno R.
Le tecniche di digitalizzazione 3D si sono fatte largo prepotentemente nel campo dei beni culturali. Dalle prime sperimentazioni dell'utilizzo di modelli 3D di due decenni fa, si è arrivati oggi ad una ampia diffusione e democratizzazione di queste tecnologie, fino a poter dire che la digitalizzazione 3D è uno strumento ormai essenziale nella maggior parte dei progetti di conservazione, restauro, documentazione e studio dei beni culturali. Nell'ultimo periodo, poi, anche le tecnologie di riproduzione fisica da modelli 3D (3D printing e la prototipazione rapida) stanno entrando nella routine di queste tipologie di azione. Un aspetto chiave dei modelli digitali 3D risiede nella loro "doppia natura": -i modelli 3D sono pura informazione numerica e geometrica, sono fatti, cioè, di numeri che rappresentano le misure e la forma di un oggetto fisico. Hanno dunque proprietà metriche, e le misure in essi contenute possono essere usate per calcoli tecnici, documentazione, simulazione e riproduzione fisica; -i modelli 3D però hanno anche un aspetto "visuale", cioè possono essere visualizzati e disegnati a schermo formando immagini che, visivamente, corrispondono alla percezione che noi avremmo davanti all'oggetto reale (specialmente quando il modello 3D geometrico è corredato anche di informazione di tessitura o colore). Questa doppia natura unisce una precisione, una scientificità del dato, alla possibilità di interagire con esso in maniera naturale, come faremmo con l'oggetto reale. Se è vero che nelle prime sperimentazioni, i modelli 3D sono stati utilizzati solamente come fonte di misure e di dati, oppure solo come "gadget visuale" per presentare al pubblico l'oggetto d'arte, possiamo dire che oggi, con il progredire delle tecnologie, e soprattutto con la definizione di protocolli di lavoro più completi, questi due aspetti riescono ad essere sfruttati appieno in maniera congiunta. In questo lavoro, per l'appunto, è stato possibile sfruttare appieno le potenzialità del media digitale 3D, sia dal punto di vista scientifico-documentale, che come strumento di disseminazione e di coinvolgimento del pubblico.Source: Alchimia di Jackson Pollock - Viaggio all'interno della materia, edited by Luciano Pensabene Buemi, Francesca Bettini, Roberto Bellucci, pp. 145–154. Firenze: Edifir - Edizioni Firenze s.r.l., 2019
Callieri M., Dellepiane M., Lureau A., Pavoni G., Pingi P., Potenziani M., Scopigno R.
Le tecniche di digitalizzazione 3D si sono fatte largo prepotentemente nel campo dei beni culturali. Dalle prime sperimentazioni dell'utilizzo di modelli 3D di due decenni fa, si è arrivati oggi ad una ampia diffusione e democratizzazione di queste tecnologie, fino a poter dire che la digitalizzazione 3D è uno strumento ormai essenziale nella maggior parte dei progetti di conservazione, restauro, documentazione e studio dei beni culturali. Nell'ultimo periodo, poi, anche le tecnologie di riproduzione fisica da modelli 3D (3D printing e la prototipazione rapida) stanno entrando nella routine di queste tipologie di azione. Un aspetto chiave dei modelli digitali 3D risiede nella loro "doppia natura": -i modelli 3D sono pura informazione numerica e geometrica, sono fatti, cioè, di numeri che rappresentano le misure e la forma di un oggetto fisico. Hanno dunque proprietà metriche, e le misure in essi contenute possono essere usate per calcoli tecnici, documentazione, simulazione e riproduzione fisica; -i modelli 3D però hanno anche un aspetto "visuale", cioè possono essere visualizzati e disegnati a schermo formando immagini che, visivamente, corrispondono alla percezione che noi avremmo davanti all'oggetto reale (specialmente quando il modello 3D geometrico è corredato anche di informazione di tessitura o colore). Questa doppia natura unisce una precisione, una scientificità del dato, alla possibilità di interagire con esso in maniera naturale, come faremmo con l'oggetto reale. Se è vero che nelle prime sperimentazioni, i modelli 3D sono stati utilizzati solamente come fonte di misure e di dati, oppure solo come "gadget visuale" per presentare al pubblico l'oggetto d'arte, possiamo dire che oggi, con il progredire delle tecnologie, e soprattutto con la definizione di protocolli di lavoro più completi, questi due aspetti riescono ad essere sfruttati appieno in maniera congiunta. In questo lavoro, per l'appunto, è stato possibile sfruttare appieno le potenzialità del media digitale 3D, sia dal punto di vista scientifico-documentale, che come strumento di disseminazione e di coinvolgimento del pubblico.Source: Alchimia di Jackson Pollock - Viaggio all'interno della materia, edited by Luciano Pensabene Buemi, Francesca Bettini, Roberto Bellucci, pp. 145–154. Firenze: Edifir - Edizioni Firenze s.r.l., 2019
See at: CNR ExploRA
2019
Journal article
Closed Access
RELIGHT: a compact and accurate RTI representation for the web
Ponchio F., Corsini M., Scopigno R.
Relightable images have been widely used as a valuable tool in Cultural Heritage (CH) artifacts, including coins, bas-reliefs, paintings, and epigraphs. Reflection Transformation Imaging (RTI), a commonly used type of relightable images, consists of a per-pixel function which encodes the reflection behavior, estimated from a set of digital photographs acquired from a fixed view. Web visualisation tools for RTI images currently require to transmit substantial quantities of data in order to achieve high fidelity renderings. We propose a web-friendly compact representation for RTI images based on a joint interpolation-compression scheme that combines a PCA-based data reduction with a Gaussian Radial Basis Function (RBF) interpolation exhibiting superior performance in terms of quality/size ratio. This approach can be adapted also to other data interpolation schemes, and it is not limited to Gaussian RBF. The rendering part is simple to implement and computationally efficient allowing real-time rendering on low-end devices.Source: Graphical models (Print) 105 (2019). doi:10.1016/j.gmod.2019.101040
DOI: 10.1016/j.gmod.2019.101040
Metrics:
Ponchio F., Corsini M., Scopigno R.
Relightable images have been widely used as a valuable tool in Cultural Heritage (CH) artifacts, including coins, bas-reliefs, paintings, and epigraphs. Reflection Transformation Imaging (RTI), a commonly used type of relightable images, consists of a per-pixel function which encodes the reflection behavior, estimated from a set of digital photographs acquired from a fixed view. Web visualisation tools for RTI images currently require to transmit substantial quantities of data in order to achieve high fidelity renderings. We propose a web-friendly compact representation for RTI images based on a joint interpolation-compression scheme that combines a PCA-based data reduction with a Gaussian Radial Basis Function (RBF) interpolation exhibiting superior performance in terms of quality/size ratio. This approach can be adapted also to other data interpolation schemes, and it is not limited to Gaussian RBF. The rendering part is simple to implement and computationally efficient allowing real-time rendering on low-end devices.Source: Graphical models (Print) 105 (2019). doi:10.1016/j.gmod.2019.101040
DOI: 10.1016/j.gmod.2019.101040
Metrics:
See at:
Graphical Models | www.sciencedirect.com | CNR ExploRA
2019
Conference article
Open Access
A complete framework operating spatially-oriented RTI in a 3D/2D cultural heritage documentation and analysis tool
Pamart A., Ponchio F., Abergel V., Alaoui M'darhri A., Corsini M., Dellepiane M., Morlet F., Scopign R., De Luca L.
Close-Range Photogrammetry (CRP) and Reflectance Transformation Imaging (RTI) are two of the most used image-based techniques when documenting and analyzing Cultural Heritage (CH) objects. Nevertheless, their potential impact in supporting study and analysis of conservation status of CH assets is reduced as they remain mostly applied and analyzed separately. This is mostly because we miss easy-to-use tools for of a spatial registration of multimodal data and features for joint visualisation gaps. The aim of this paper is to describe a complete framework for an effective data fusion and to present a user friendly viewer enabling the joint visual analysis of 2D/3D data and RTI images. This contribution is framed by the on-going implementation of automatic multimodal registration (3D, 2D RGB and RTI) into a collaborative web platform (AIOLI) enabling the management of hybrid representations through an intuitive visualization framework and also supporting semantic enrichment through spatialized 2D/3D annotations.Source: 8th International Workshop 3D-ARCH "3D Virtual Reconstruction and Visualization of Complex Architectures", pp. 573–580, Bergamo, Italy, 6-8 February 2019
DOI: 10.5194/isprs-archives-xlii-2-w9-573-2019
Metrics:
Pamart A., Ponchio F., Abergel V., Alaoui M'darhri A., Corsini M., Dellepiane M., Morlet F., Scopign R., De Luca L.
Close-Range Photogrammetry (CRP) and Reflectance Transformation Imaging (RTI) are two of the most used image-based techniques when documenting and analyzing Cultural Heritage (CH) objects. Nevertheless, their potential impact in supporting study and analysis of conservation status of CH assets is reduced as they remain mostly applied and analyzed separately. This is mostly because we miss easy-to-use tools for of a spatial registration of multimodal data and features for joint visualisation gaps. The aim of this paper is to describe a complete framework for an effective data fusion and to present a user friendly viewer enabling the joint visual analysis of 2D/3D data and RTI images. This contribution is framed by the on-going implementation of automatic multimodal registration (3D, 2D RGB and RTI) into a collaborative web platform (AIOLI) enabling the management of hybrid representations through an intuitive visualization framework and also supporting semantic enrichment through spatialized 2D/3D annotations.Source: 8th International Workshop 3D-ARCH "3D Virtual Reconstruction and Visualization of Complex Architectures", pp. 573–580, Bergamo, Italy, 6-8 February 2019
DOI: 10.5194/isprs-archives-xlii-2-w9-573-2019
Metrics:
See at:
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | ISTI Repository | ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | Hyper Article en Ligne | CNR ExploRA
2019
Conference article
Open Access
A Validation Tool For Improving Semantic Segmentation of Complex Natural Structures
Pavoni G., Corsini M., Palma M., Scopigno R.
The automatic recognition of natural structures is a challenging task in the supervised learning field. Complex morphologies are difficult to detect both from the networks, that may suffer from generalization issues, and from human operators, affecting the consistency of training datasets. The task of manual annotating biological structures is not comparable to a generic task of detecting an object (a car, a cat, or a flower) within an image. Biological structures are more similar to textures, and specimen borders exhibit intricate shapes. In this specific context, manual labelling is very sensitive to human error. The interactive validation of the predictions is a valuable resource to improve the network performance and address the inaccuracy caused by the lack of annotation consistency of human operators reported in literature. The proposed tool, inspired by the Yes/No Answer paradigm, integrates the semantic segmentation results coming from a CNN with the previous human labeling, allowing a more accurate annotation of thousands of instances in a short time. At the end of the validation, it is possible to obtain corrected statistics or export the integrated dataset and re-train the network.Source: Eurographics 2019, pp. 57–60, Genova, 6/5/2019-10/5/2019
DOI: 10.2312/egs.20191014
Metrics:
Pavoni G., Corsini M., Palma M., Scopigno R.
The automatic recognition of natural structures is a challenging task in the supervised learning field. Complex morphologies are difficult to detect both from the networks, that may suffer from generalization issues, and from human operators, affecting the consistency of training datasets. The task of manual annotating biological structures is not comparable to a generic task of detecting an object (a car, a cat, or a flower) within an image. Biological structures are more similar to textures, and specimen borders exhibit intricate shapes. In this specific context, manual labelling is very sensitive to human error. The interactive validation of the predictions is a valuable resource to improve the network performance and address the inaccuracy caused by the lack of annotation consistency of human operators reported in literature. The proposed tool, inspired by the Yes/No Answer paradigm, integrates the semantic segmentation results coming from a CNN with the previous human labeling, allowing a more accurate annotation of thousands of instances in a short time. At the end of the validation, it is possible to obtain corrected statistics or export the integrated dataset and re-train the network.Source: Eurographics 2019, pp. 57–60, Genova, 6/5/2019-10/5/2019
DOI: 10.2312/egs.20191014
Metrics:
See at:
diglib.eg.org | ISTI Repository | CNR ExploRA