CVPR2025 GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

X-Avatar: Expressive Human Avatars (CVPR2023)

Code of LAM: Large Avatar Model for One-shot Animatable Gaussian Head

[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

Character Animation (AnimateAnyone, Face Reenactment)

Taming Stable Diffusion for Lip Sync!

Code for the paper "Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters"

[ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

[NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko,…

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Implementation for 3d gaussian splatting

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Official PyTorch Implementation of EDGE (CVPR 2023)

Precomputed Radiance Transfer for Real-Time Rendering in Dynamic, Low-Frequency Lighting Environments

Training and Evaluation Code for "Mixture of Volumetric Primitives for Efficient Neural Rendering"

Official repository of HUGS: Human Gaussian Splats (CVPR 2024)

try to export sam2 to onnx.

MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]

Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

基于计算机视觉手势识别控制系统YoLoGesture (利用YOLO实现)，利用yolo进行手势识别的控制系统，最后利用streamlit进行了部署，可在线体验尝试https://kedreamix-yologesture.streamlit.app , huggingface也有https://huggingface.co/spaces/Kedreamix/YoloGesture ，除此之…

Differential Gaussian Rasterization with Depth forward and backward functionality

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.