Code Release for DiffusionRig (CVPR 2023)

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

[SIGGRAPH 2024] InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars

Repository of the paper "AnyUp: Universal Feature Upsampling".

D3-Human: Dynamic Disentangled Digital Human from Monocular Video

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

[SIGGRAPH Asia 2024] FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Images

[SIGGRAPH 2025 Asia] The official repo for the conference paper "MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis".

Code release for paper "Test-Time Training Done Right"

Self-reimplemented version of Long-LRM.

Self-reimplemented version of 4D-LRM.

[NeurIPS 2025]SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.

Official repository for the paper "MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars"

Dynamic 3D Foundation Model using Causal Transformer

[3DV'25] 3D Reconstruction with Spatial Memory

[NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

Code for Streaming 4D Visual Geometry Transformer

A simple state update rule to enhance length generalization for CUT3R

Official implementation of Continuous 3D Perception Model with Persistent State

Official EHM Tracking Implementation for GUAVA (ICCV 2025)

Inference code to "Adversarially-Guided Portrait Matting"

Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 24); Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer (ECCV 2024)

COLMAP - Structure-from-Motion and Multi-View Stereo

Official Repository of [CVPR'25 Paper Diffportrait360: Consistent portrait diffusion for 360 view synthesis

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

The human face subset of LAION-400M for large-scale face pretraining.

FaRL for Facial Representation Learning [Official, CVPR 2022]

Face analysis tools for modern research, equipped with state-of-the-art Face Parsing and Face Alignment

⚡Batch Face Processing for Fast Modern Research, including face detection, face alignment, face reconstruction, head pose estimation, face parsing