2020
Journal article  Open Access

Real-World textured things: a repository of textured models generated with modern photo-reconstruction tools

Maggiordomo A., Ponchio F., Cignoni P., Tarini M.

Parametrization  Modeling and Simulation  Settore INF/01 - Informatica  Dataset  Benchmarks  Computer Graphics and Computer-Aided Design  Real-world models  Texture  Graphics (cs.GR)  Textures  FOS: Computer and information sciences  Quality measurement  Photogrammetry-based 3D reconstruction  Benchmark  Surface parametrization  Aerospace Engineering  Automotive Engineering  Computer Science - Graphics 

We are witnessing a proliferation of textured 3D models captured from the real world with automatic photo-reconstruction tools by people and professionals without a proper technical background in computer graphics. Digital 3D models of this class come with a unique set of characteristics and defects - especially concerning their parametrization - setting them starkly apart from 3D models originating from other, more traditional, sources. We study this class of 3D models by collecting a significant number of representatives and quantitatively evaluating their quality according to several metrics. These include a new invariant metric we carefully design to assess the amount of fragmentation of the UV map, which is one of the main weaknesses potentially hindering the usability of these models. Our results back the widely shared notion that models of this new class are still not fit for direct use in downstream applications (such as videogames), and require challenging processing steps. Regrettably, existing automatic geometry processing tools are not always up to the task: for example, we verify that the available tools for UV optimization often fail due to mesh inconsistencies, geometric and topological noise, excessive resolution, or other factors; moreover, even when an output is produced, it rarely represents a significant improvement over the input (according to the aforementioned measures). Therefore, we argue that further advancements are required by the computer graphics and geometry processing communities specifically targeted at this class of models. Towards this goal, we share the models we collected in this study as a new public repository, Real-World Textured Things (RWTT), intended as a benchmark to systematic field-test and compare future algorithms. RWTT consists of 568 carefully selected textured 3D models representative of the most popular photo-reconstruction tools currently available. We also provide a web interface to browse the dataset by the metadata we collected during our experiments and a tool, TexMetro, to compute the same set of measures on generic UV mapped datasets.

Source: Computer aided geometric design 83 (2020). doi:10.1016/j.cagd.2020.101943

Publisher: North-Holland, Amsterdam , Paesi Bassi


3DFlow, 2014{2018. Zephyr. https://www.3dflow.net/3df-zephyr-pro-3d-models-from-photos/.
Agisoft LLC, 2010{2018. Photoscan: photogrammetric processing of digital images and 3d spatial data generation. http: //www.agisoft.com.
Attene, M., Campen, M., Kobbelt, L., 2013. Polygon mesh repairing: An application perspective. ACM Comput. Surv. 45. URL: https://doi.org/10.1145/2431211.2431214, doi:10.1145/2431211.2431214.
Autodesk, I., 2018. ReCap: Create accurate 3D models with reality capture. https://www.autodesk.com/products/recap/ overview.
Autodesk, Inc, 2019. Autodesk Maya 2019. https://www.autodesk.com/products/maya/overview.
Bentley, 2014{2018. ContextCapture. https://www.bentley.com/en/products/brands/contextcapture/.
Blender Foundation, 2019. Blender - Free and Open 3D Creation Software. URL: http://www.blender.org.
CapturingReality, 2014{2018. RealityCapture: state-of-the-art all-in-one photogrammetry software solution. https://www. capturingreality.com/Product/.
Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., Xiao, J., Yi, L., Yu, F., 2015. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR]. Stanford University | Princeton University | Toyota Technological Institute at Chicago.
Choi, S., Zhou, Q.Y., Miller, S., Koltun, V., 2016. A large dataset of object scans. arXiv:1602.02481 .

Metrics



Back to previous page
BibTeX entry
@article{oai:it.cnr:prodotti:434543,
	title = {Real-World textured things: a repository of textured models generated with modern photo-reconstruction tools},
	author = {Maggiordomo A. and Ponchio F. and Cignoni P. and Tarini M.},
	publisher = {North-Holland, Amsterdam , Paesi Bassi},
	doi = {10.1016/j.cagd.2020.101943 and 10.48550/arxiv.2004.14753},
	journal = {Computer aided geometric design},
	volume = {83},
	year = {2020}
}

ENCORE
ENergy aware BIM Cloud Platform in a COst-effective Building REnovation Context


OpenAIRE