Goel, Shubham and Gkioxari, Georgia and Malik, Jitendra (2022) Differentiable Stereopsis: Meshes from multiple views using differentiable rendering. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , Piscataway, NJ, pp. 8625-8634. ISBN 978-1-6654-6946-3. https://resolver.caltech.edu/CaltechAUTHORS:20221215-789792000.24
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20221215-789792000.24
Abstract
We propose Differentiable Stereopsis, a multi-view stereo approach that reconstructs shape and texture from few input views and noisy cameras. We pair traditional stereopsis and modern differentiable rendering to build an end-to-end model which predicts textured 3D meshes of objects with varying topologies and shape. We frame stereopsis as an optimization problem and simultaneously update shape and cameras via simple gradient descent. We run an extensive quantitative analysis and compare to traditional multi-view stereo techniques and state-of-the-art learning based methods. We show compelling reconstructions on challenging real-world scenes and for an abundance of object types with complex shape, topology and texture. Project webpage: https://shubham-goel.github.io/ds/
Item Type: | Book Section | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Related URLs: |
| |||||||||
ORCID: |
| |||||||||
DOI: | 10.1109/cvpr52688.2022.00844 | |||||||||
Record Number: | CaltechAUTHORS:20221215-789792000.24 | |||||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20221215-789792000.24 | |||||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | |||||||||
ID Code: | 118381 | |||||||||
Collection: | CaltechAUTHORS | |||||||||
Deposited By: | George Porter | |||||||||
Deposited On: | 19 Dec 2022 20:34 | |||||||||
Last Modified: | 19 Dec 2022 23:14 |
Repository Staff Only: item control page