https://github.com/hassony2/shape_sdf
https://github.com/hassony2/shape_sdf
neural-network shape shape-reconstruction signed-distance-field
Last synced: 5 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/hassony2/shape_sdf
- Owner: hassony2
- Created: 2019-01-26T18:01:44.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2019-04-01T20:31:08.000Z (about 7 years ago)
- Last Synced: 2024-05-31T18:22:55.584Z (almost 2 years ago)
- Topics: neural-network, shape, shape-reconstruction, signed-distance-field
- Language: Python
- Size: 45.9 KB
- Stars: 44
- Watchers: 7
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-3D-vision - DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
README
# Predicting shapes as implicit functions
## Predicting signed-distance functions from points clouds using neural networks
## References
**Very** similar ideas are presented in the following papers (all put online between December 2018 and January 2019!):
[Occupancy Networks: Learning 3D Reconstruction in Function Space](https://arxiv.org/pdf/1812.03828v1.pdf)
[DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://arxiv.org/pdf/1901.05103.pdf)
[Deep Level Sets: Implicit Surface Representations for 3D Shape Inference](https://arxiv.org/pdf/1901.06802.pdf)
[Learning Implicit Fields for Generative Shape Modeling](https://arxiv.org/pdf/1812.02822.pdf)