Abstract | ||
---|---|---|
Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature. While template-based approaches, such as parametric shape models, have achieved great success in modeling the "closed world" of known object categories, they cannot well handle the "open-world" of novel object categories or outlier shapes. In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthesis strategy that forward-renders object silhouette, optical flow, and pixel values to compare with video observations, which generates gradients to adjust the camera, shape and motion parameters. Without using a category-specific shape template, our method faithfully reconstructs nonrigid 3D structures from videos of human, animals, and objects of unknown classes. Our code is available at lasr-google.github.io. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPR46437.2021.01572 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gengshan Yang | 1 | 15 | 3.34 |
Deqing Sun | 2 | 1061 | 44.84 |
Varun Jampani | 3 | 184 | 19.44 |
Daniel Vlasic | 4 | 1 | 1.03 |
Forrester Cole | 5 | 420 | 20.41 |
Huiwen Chang | 6 | 26 | 4.73 |
deva ramanan | 7 | 10678 | 566.72 |
William T. Freeman | 8 | 17382 | 1968.76 |
Ce Liu | 9 | 3347 | 188.04 |