Lists (6)
Stars
CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.
Interactive visualizations of the geometric intuition behind diffusion models.
[CVPR 2025] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
Code of Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Field. ACM Transactions on Graphics (SIGGRAPH 2023).
collect papers about human motion capture
Code for "MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space"
The modified 272-dimensional motion representation processing script.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
[CVPR 2023] MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
[Siggraph Asia 2024] Follow-Your-Emoji: This repo is the official implementation of "Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation"
Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (ECCV2022)
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
[SIGGRAPH 2025] AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing
DreamO: A Unified Framework for Image Customization
Awesome Unified Multimodal Models
CUDA Python: Performance meets Productivity
An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Motion imitation with deep reinforcement learning.
[Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos