https://github.com/lyteabovenyte/3d_computer_vision
Covering 3D computer vision concepts and implementations from state-of-the-art papers
https://github.com/lyteabovenyte/3d_computer_vision
3d-models computer-vision control-systems physics-based-neuralnetwork pytorch3d
Last synced: 8 days ago
JSON representation
Covering 3D computer vision concepts and implementations from state-of-the-art papers
- Host: GitHub
- URL: https://github.com/lyteabovenyte/3d_computer_vision
- Owner: lyteabovenyte
- Created: 2025-04-15T11:52:00.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-12T18:42:15.000Z (about 1 year ago)
- Last Synced: 2025-05-12T19:21:29.404Z (about 1 year ago)
- Topics: 3d-models, computer-vision, control-systems, physics-based-neuralnetwork, pytorch3d
- Language: Python
- Homepage:
- Size: 2.84 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
#### Concepts and Implementation of the state-of-the-art models and architecture in the field of 3D computer vision
#### list of papers:
- [Point-Net](https://arxiv.org/pdf/1612.00593)
- [Point-MAE](https://arxiv.org/abs/2203.06604)
- [Point-M2AE](https://arxiv.org/abs/2205.14401)
- [PointGroup](https://arxiv.org/abs/2004.01658)
- [You Only Need One Thing One Click](https://arxiv.org/abs/2303.14727)
- [DGCNN- dynamic graph CNN for learning on Point Clouds](https://arxiv.org/abs/1801.07829)
- [Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder](https://arxiv.org/abs/2311.10887)
- [Learning 3D Dynamic Scene Representations for Robot Manipulation](https://arxiv.org/abs/2011.01968)
- [Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning](https://arxiv.org/abs/2009.05085)
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://arxiv.org/pdf/2104.11224)
- [Model-based Reinforcement Learning for Parameterized Action Spaces](https://arxiv.org/pdf/2404.03037v3)
- [Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning](https://arxiv.org/pdf/2009.05085)
- [NeRF: Neural Radiance Field in 3D Vision, Introduction and Review](https://arxiv.org/pdf/2210.00379)
- [Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids](http://dpi.csail.mit.edu/dpi-paper.pdf)
- [Propagation Networks for Model-Based Control Under Partial Observation](https://arxiv.org/pdf/1809.11169)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://arxiv.org/pdf/1907.10844)
- [PU-Net: Point Cloud Upsampling Network](https://arxiv.org/pdf/1801.06761)
- [SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization](https://arxiv.org/abs/2012.04439)
-
###### I'll try to train simplified version of each architecture and provide the weights along side a docker image which will be placed here after compeletion.