IEEE Transactions on Pattern Analysis and Machine Intelligence· 2014Q1
Shape, Illumination, and Reflectance from Shading
- 661citations
- Q1SCImago
- 2014year
Short summary
This paper introduces a novel statistical inference approach to recover 3D scene properties like shape, reflectance, and illumination from a single 2D image, overcoming the limitations of traditional multi-observation methods.
AI-generated from the title and abstract; the full text is not read.
Key points
- Enables recovery of 3D scene properties (shape, reflectance, illumination) from a single 2D image.
- Uses a statistical inference optimization problem based on likelihood assumptions (e.g., smooth surfaces, natural light).
- Acts as a superset of classic computer vision problems like shape-from-shading and color constancy.
- Outperforms previous solutions for these constituent problems.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Graphics and Computer-Aided Design
Computer Graphics and Computer-Aided DesignComputer Science