Visual Geometry Group company blog
Unsupervised learning of probably symmetric deformable 3D objects from images
We propose a method to learn weakly symmetric deformable 3D object categories from raw single-view images, without ground-truth 3D, multiple views, 2D/3D keypoints, prior shape models or any other supervision.
- Points
- 181
- HN comments
- 35
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningScience & Space2020
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Mar 25, 2020 | Unsupervised learning of probably symmetric deformable 3D objects from images by jotaf | 181 | 35 |
