Starred repositories
An unofficial implementation of the paper "ObjectStitch: Object Compositing with Diffusion Model", CVPR 2023.
Image composition toolbox: everything you want to know about image composition or object insertion
[AAAI 2026] Personalize Anything for Free with Diffusion Transformer
An unofficial and simplified implementation of SIGGRAPH 2025 best paper nominate: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image, working in progress
[ICLR 2025] Official implementation of "DiffSplat: Repurposing Image Diffusion Models for Scalable 3D Gaussian Splat Generation".
[ECCV 2024] BlenderAlchemy: Editing 3D Graphics with Vision-Language Models
[ICCV 2025] This repo is the official implementation of "Multi-Object Sketch Animation by Scene Decomposition and Motion Planning"
A trusty face analysis research platform developed by Tencent Youtu Lab
[CVPR2024] Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion
Dynamic Gaussian Mesh: Consistent Mesh Reconstruction from Monocular Videos (ICLR 2025)
The source code of the paper "RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos"
[ICCV 2021] A dataset of non-rigidly deforming objects.
AcadHomepage: A Modern and Responsive Academic Personal Homepage
[ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
[SIGGRAPH 2025] Official code of the paper "FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios"
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
[CVPR 2025] Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
[CVPR'25] Official Implementations for Paper - AniDoc: Animation Creation Made Easier
FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"
[CVPR'24] DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
[SIGGRAPH'25] SOAP: Style-Omniscient Animatable Portraits
Official Implementation of [AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models]
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"