Stars
Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
[CVPR'25] Official repository for "Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration"
Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction…
Talking Head (3D): A JavaScript class for real-time lip-sync using Ready Player Me full-body 3D avatars.
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.
Real time interactive streaming digital human
[ICCV 2025] GaussianSpeech: Audio-Driven Gaussian Avatars
Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"
Official code for paper "InstantSfM: Fully Sparse and Parallel Structure-from-Motion"
[SIGGRAPH Asia 2025] 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025)
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
DNA-RENDERING: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
High-resolution models for human tasks.
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Official repo for "Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field"
Code for FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
[CVPR 2025] CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
The dataset of the paper "Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos".
Official implementation of TaoGS (Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos)
CoTracker is a model for tracking any point (pixel) on a video.