Stars
UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers
Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"
Code for "Differentiable Robot Rendering" (CoRL 2024)
[ECCV 2024] Code for "EraseDraw: Learning to Insert Objects by Erasing Them from Images"
From Imitation to Refinement -- Residual RL for Precise Visual Assembly
DayDreamer: World Models for Physical Robot Learning
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation (CoRL 2024)
CUDA accelerated rasterization of gaussian splatting
Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation
Pandora: Towards General World Model with Natural Language Actions and Video States
Using advances in generative modeling to learn reward functions from unlabeled videos.
Robot kinematics implemented in pytorch
iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching
[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM
[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"
[CVPR 2025] StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
PaperBot: Learning to Design Real-World Tools Using Paper
Original reference implementation of "GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering" [CVPR 2024]
Code for the paper "pix2gestalt: Amodal Segmentation by Synthesizing Wholes" (CVPR 2024)
Multi-Joint dynamics with Contact. A general purpose physics simulator.
[CoRL 2023] This repository contains data generation and training code for Scaling Up & Distilling Down
MuJoCo Models for Google's Scanned Objects Dataset