Back to Search
Start Over
A L1-TV Algorithm for Robust Perspective Photometric Stereo with Spatially-Varying Lightings
- Source :
- 5th International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2015), 5th International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2015), May 2015, Lège Cap Ferret, France. pp. 498-510, Lecture Notes in Computer Science ISBN: 9783319184609, SSVM
- Publication Year :
- 2015
- Publisher :
- HAL CCSD, 2015.
-
Abstract
- International audience; We tackle the problem of perspective 3D-reconstruction of Lambertian surfaces through photometric stereo, in the presence of outliers to Lambert’s law, depth discontinuities, and unknown spatially-varying lightings. To this purpose, we introduce a robust L1-TV variational formulation of the recovery problem where the shape itself is the main unknown, which naturally enforces integrability and permits to avoid integrating the normal field.
- Subjects :
- Perspective projection
Computer science
02 engineering and technology
Proximal methods
Classification of discontinuities
01 natural sciences
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Traitement des images
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing
0202 electrical engineering, electronic engineering, information engineering
Traitement du signal et de l'image
Computer vision
0101 mathematics
Synthèse d'image et réalité virtuelle
Uncalibrated photometric stereo
Total variation
business.industry
Perspective (graphical)
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Vision par ordinateur et reconnaissance de formes
Intelligence artificielle
[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]
010101 applied mathematics
Normal field
Photometric stereo
Spatialisation
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
Outlier
Spatially-varying lightings
020201 artificial intelligence & image processing
Artificial intelligence
business
Algorithm
Subjects
Details
- Language :
- English
- ISBN :
- 978-3-319-18460-9
- ISBNs :
- 9783319184609
- Database :
- OpenAIRE
- Journal :
- 5th International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2015), 5th International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2015), May 2015, Lège Cap Ferret, France. pp. 498-510, Lecture Notes in Computer Science ISBN: 9783319184609, SSVM
- Accession number :
- edsair.doi.dedup.....7524dd9353118ee127b3abbbb01c16b4
- Full Text :
- https://doi.org/10.1007/978-3-319-18461-6