Coherence as Texture - Passive Textureless 3D Reconstruction by Self-Interference
Abstract
Passive depth estimation based on stereo or defocus relies on the presence of the texture on an object to resolve its depth. Hence recovering the depth of a textureless object-- for example a large white wall--is not just hard but perhaps even impossible. Or is it? We show that spatial coherence a property of natural light sources can be used to resolve the depth of a scene point even when it is textureless. Our approach relies on the idea that natural light scattered off a scene point is locally coherent with itself while incoherent with the light scattered from other surface points; we use this insight to design an optical setup that uses self-interference as a texture feature for estimating depth. Our lab prototype is capable of resolving the depths of textureless objects in sunlight as well as indoor lights.
Cite
Text
Chen et al. "Coherence as Texture - Passive Textureless 3D Reconstruction by Self-Interference." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.02367Markdown
[Chen et al. "Coherence as Texture - Passive Textureless 3D Reconstruction by Self-Interference." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/chen2024cvpr-coherence/) doi:10.1109/CVPR52733.2024.02367BibTeX
@inproceedings{chen2024cvpr-coherence,
title = {{Coherence as Texture - Passive Textureless 3D Reconstruction by Self-Interference}},
author = {Chen, Wei-Yu and Sankaranarayanan, Aswin C. and Levin, Anat and O'Toole, Matthew},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {25058-25066},
doi = {10.1109/CVPR52733.2024.02367},
url = {https://mlanthology.org/cvpr/2024/chen2024cvpr-coherence/}
}