What is it about?
Accurately capturing the reflectance of real-world materials has been a longstanding problem in computer graphics and computer vision. This method estimates material properties from a single image casually captured under a planar light source. The key idea is to maximize the capture efficiency of a single image using a learned lighting pattern.
Featured Image
Photo by Suganth on Unsplash
Why is it important?
The method improves the capture efficiency of a single image significantly by learning the lighting pattern of a planar light source, and reconstructs high-quality SVBRDF by learning the global correlation prior of the input image.
Perspectives
By writing this article, I hope that I can bring the community some different thoughts on appearance reconstruction.
Lianghao Zhang
Tianjin University
Read the Original
This page is a summary of: Deep SVBRDF Estimation from Single Image under Learned Planar Lighting, July 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3588432.3591559.
You can read the full text:
Contributors
The following have contributed to this page
