Journal article  Restricted

State-of-the-art in Automatic 3D Reconstruction of Structured Indoor Environments

Pintore G., Mura C., Ganovelli F., Fuentes-perez L., Pajarola R., Gobbetti E.

Reconstruction  Computer vision  Applied computing  Computer vision problems  Computer graphics  CCS Concepts  Computing methodologies  Shape modeling  Shape inference  Computer-aided design  Computer Networks and Communications 

Creating high-level structured 3D models of real-world indoor scenes from captured data is a fundamental task which has important applications in many fields. Given the complexity and variability of interior environments and the need to cope with noisy and partial captured data, many open research problems remain, despite the substantial progress made in the past decade. In this survey, we provide an up-to-date integrative view of the field, bridging complementary views coming from computer graphics and computer vision. After providing a characterization of input sources, we define the structure of output models and the priors exploited to bridge the gap between imperfect sources and desired output. We then identify and discuss the main components of a structured reconstruction pipeline, and review how they are combined in scalable solutions working at the building level. We finally point out relevant research issues and analyze research trends.

Source: Computer graphics forum (Print) 39 (2020): 667–699. doi:10.1111/cgf.14021

Publisher: Basil Blackwell Publishers, Oxford , Paesi Bassi

Back to previous page
Projects (via OpenAIRE)

Advanced Visual and Geometric Computing for 3D Capture, Display, and Fabrication

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

BibTeX entry
	title = {State-of-the-art in Automatic 3D Reconstruction of Structured Indoor Environments},
	author = {Pintore G. and Mura C. and Ganovelli F. and Fuentes-perez L. and Pajarola R. and Gobbetti E.},
	publisher = {Basil Blackwell Publishers, Oxford , Paesi Bassi},
	doi = {10.1111/cgf.14021},
	journal = {Computer graphics forum (Print)},
	volume = {39},
	pages = {667–699},
	year = {2020}