
pytorch-dense-correspondence
by RobotLocomotion (organization)
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation" (description from the project’s GitHub page)
Repository facts
- Stars
- 575
- Forks
- 135
- Open issues and pull requests
- 11
- Primary language
- Python
- License
- Other license
- Owner
- RobotLocomotion · Organization
- Created
- Feb 13, 2018
- Last push
- May 9, 2023
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 5,681: andyzeng/visual-pushing-grasping
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
1,114 starsPythonBSD-2-ClauseLast push May 11, 2021
Rank 6,123: mees/calvin
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
999 starsPythonMITLast push Sep 8, 2025
Rank 9,045: cliport/cliport
CLIPort: What and Where Pathways for Robotic Manipulation
547 starsJupyter NotebookApache-2.0Last push Nov 2, 2023
Rank 7,839: wenbowen123/BundleTrack
[IROS 2021] BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
687 starsC++Apache-2.0Last push Apr 13, 2026
Rank 6,497: andyzeng/3dmatch-toolbox
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
907 starsC++BSD-2-ClauseLast push Oct 14, 2025
Rank 7,987: Megvii-BaseDetection/cvpods
All-in-one Toolbox for Computer Vision Research.
663 starsPythonApache-2.0Last push Mar 10, 2023