Multi-view Multi-illuminant Intrinsic Dataset

Shida Beigpour, Mai Lan Ha, Sven Kunz, Andreas Kolb and Volker Blanz

Abstract

This paper proposes a novel high-resolution multi-view dataset of complex multi-illuminant scenes with precise reflectance and shading ground-truth as well as raw depth and 3D point cloud. Our dataset challenges the intrinsic image methods by providing complex coloured cast shadows, highly textured and colourful surfaces, and specularity. This is the first publicly available multi-view real-photo dataset at such complexity with pixel-wise intrinsic ground-truth. In the effort to help evaluating different intrinsic image methods, we propose a new perception-inspired metric based on the reflectance consistency. We provide the evaluation of three intrinsic image methods using our dataset and metric.

Session

Posters 1

Files

PDF iconExtended Abstract (PDF, 9M)
PDF iconPaper (PDF, 9M)

DOI

10.5244/C.30.10
https://dx.doi.org/10.5244/C.30.10

Citation

Shida Beigpour, Mai Lan Ha, Sven Kunz, Andreas Kolb and Volker Blanz. Multi-view Multi-illuminant Intrinsic Dataset. In Richard C. Wilson, Edwin R. Hancock and William A. P. Smith, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 10.1-10.13. BMVA Press, September 2016.

Bibtex

        @inproceedings{BMVC2016_10,
        	title={Multi-view Multi-illuminant Intrinsic Dataset},
        	author={Shida Beigpour, Mai Lan Ha, Sven Kunz, Andreas Kolb and Volker Blanz},
        	year={2016},
        	month={September},
        	pages={10.1-10.13},
        	articleno={10},
        	numpages={13},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.10},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.10}
        }