Jonathan Barron and Jitendra Malik

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2013-117

May 29, 2013

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2013/EECS-2013-117.pdf

A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely on multiple observations of the same scene to overconstrain the problem. Recovering these same properties from a single image seems almost impossible in comparison --- there are an infinite number of shapes, paint, and lights that exactly reproduce a single image. However, certain explanations are more likely than others: surfaces tend to be smooth, paint tends to be uniform, and illumination tends to be natural. We therefore pose this problem as one of statistical inference, and define an optimization problem that searches for the most likely explanation of a single image. Our technique can be viewed as a superset of several classic computer vision problems (shape-from-shading, intrinsic images, color constancy, illumination estimation, etc) and outperforms all previous solutions to those constituent problems.

---

BibTeX citation:

@techreport{Barron:EECS-2013-117,
    Author= {Barron, Jonathan and Malik, Jitendra},
    Title= {Shape, Illumination, and Reflectance from Shading},
    Year= {2013},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2013/EECS-2013-117.html},
    Number= {UCB/EECS-2013-117},
    Abstract= {A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely on multiple observations of the same scene to overconstrain the problem. Recovering these same properties from a single image seems almost impossible in comparison --- there are an infinite number of shapes, paint, and lights that exactly reproduce a single image. However, certain explanations are more likely than others: surfaces tend to be smooth, paint tends to be uniform, and illumination tends to be natural. We therefore pose this problem as one of statistical inference, and define an optimization problem that searches for the most likely explanation of a single image. Our technique can be viewed as a superset of several classic computer vision problems (shape-from-shading, intrinsic images, color constancy, illumination estimation, etc) and outperforms all previous solutions to those constituent problems.},
}

EndNote citation:

%0 Report
%A Barron, Jonathan 
%A Malik, Jitendra 
%T Shape, Illumination, and Reflectance from Shading
%I EECS Department, University of California, Berkeley
%D 2013
%8 May 29
%@ UCB/EECS-2013-117
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2013/EECS-2013-117.html
%F Barron:EECS-2013-117