Official PyTorch implementation of "Let RGB Be the Language of Vision".

VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

Efficient vision foundation models for high-resolution generation and perception.

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

[NeurIPS'25] VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

StreamDiffusion, Live Stream APP

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

Implementation of "Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation" from CVPR Workshop on Human Motion Generation 2024.

4DHumans: Reconstructing and Tracking Humans with Transformers

[ECCV 2024] Official Code for "WHAC: World-grounded Humans and Cameras"

Our model BUDDI learns the joint distribution of interacting people

Pytorch implementation for A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose

Main OpenCap processing pipeline

This repo equips the official CLIFF [ECCV 2022 Oral] with better detector, better tracker. Support multi-person, motion interpolation, motion smooth and SMPLify fitting.

Repository for ICCV23 paper: "ReFit: Recurrent Fitting Network for 3D Human Recovery"

The official PyTorch code for RoHM: Robust Human Motion Reconstruction via Diffusion.

Official Code for Tracking Any Object Amodally

This repository is an integration of Mask RCNN (object detection and segmentation) and ROS to implement automated pick and place operation using the UR10 robot arm.

The official implementation of the paper "Human Motion Diffusion as a Generative Prior"

Release for the Siggraph Asia 2023 SKEL paper "From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans".

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

The official PyTorch implementation of the paper "Human Motion Diffusion Model"