liheyuan

image-to-3d. Python

img2threejs. Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

3DGen-R1. [CVPR 2026] The official implementation of The paper "Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation"

v2rayfree. v2ray节点、免费节点、免费v2ray节点、最新公益免费v2ray节点订阅地址、免费v2ray节点每日更新、免费ss/v2ray/trojan节点、freefq

ml-headsup. HTML

nersemble-benchmark. Python

HDTF. the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"

sapiens2. 1K resolution vision transformers pretrained on 1B human images.

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

nova3r. [ICLR 2026] NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

Hunyuan3D-2.1. From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

3D-FaceReconstruction. 3D-FaceReconstruction is a Python-based pipeline that reconstructs high-quality 3D facial meshes from a single 2D image. It integrates facial landmark detection, mesh generation, texture mapping, and depth estimation, making it ideal for applications in AR/VR, gaming, and digital avatars.

Fast-SAM-3D-Body. [ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery

SOMA-X. SOMA: Unifying Parametric Human Body Models

LHM-plusplus. LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D

DSFNet. Code for DSFNet: Dual Space Fusion Network for Occlusion-Robust Dense 3D Face Alignment

MatAnyone2. [CVPR 2026 Highlight] MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator

HyPlaneHead. [NeurIPS 2025] HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis

FaceCam. [CVPR 2026] FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning

FaceID-6M. Python

GSM. Gaussian Shell Maps for Efficient 3D Human Generation (CVPR 2024)

DELTA. Learning Disentangled Avatars with Hybrid 3D Representations. (Face, Body, Hair and Clothing)

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

InfVSR.

Mead. MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation [ECCV2020]

LHM_Track. LHM Video Dataset processing

ReliTalk. [IJCV 2024] Code for ReliTalk

Im2Haircut. Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars [ICCV 2025]

SoulX-FlashTalk. SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.

StreamingTalker. Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral

Multi-human-Talking-Video-Dataset. Muti-human Interactive Talking Dataset

Awesome-Talking-Head-Synthesis. 💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

ARTalk. ARTalk generates realistic 3D head motions (lip sync, blinking, expressions, head poses) from audio in ⚡ real-time ⚡.

DiffPoseTalk. DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models

Marigold. [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

EAMM. Code for paper 'EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model'

s3od. [ICLR 2026] Official repo for S3OD: Towards Generalizable Salient Object Detection with Synthetic Data

inferno. 🔥🔥🔥 Set the world of 3D faces on fire with INFERNO 🔥🔥🔥

AGORA. Real-time 3DGS avatars on mobile devices.

3d-multiview-inversion. [VISAPP24] Official implementation of https://arxiv.org/pdf/2312.05330.pdf

cgs-gan. [NeurIPS '25] Create 3DGS heads from latent vectors

VOODOO3D-official. Official implementation for the paper "VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment"

float. [ICCV 2025] Official Pytorch Implementation of FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait.

AvatarForcing. [CVPR 2026] Official Pytorch implementation of Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Taobao3D. C++

MHR. Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.

pixio. [CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction

Real3DPortrait. Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis; ICLR 2024 Spotlight; Official code

dreamsim. DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

facebuilder. Python Implementation of Keentools' Facebuilder Application.

StereoPilot. The official implementation of StereoPilot

HunyuanPortraitLCM. [CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

Deep-Live-Cam. real time face swap and one-click video deepfake with only a single image

awesome-spatial-intelligence. 🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

LiveAvatar. [ECCV 2026 Oral] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"

flare. [SIGGRAPH Asia '23] FLARE: Fast Learning of Animatable and Relightable Mesh Avatars

talking-face-arxiv-daily. 🎓 Update Talking-Face Research Papers Daily

StableAvatar. We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

StableAnimator. [CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

ACTalker. ICCV 2025 ACTalker: an end-to-end video diffusion framework for talking head synthesis that supports both single and multi-signal control (e.g., audio, expression).

FlashPortrait. [CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

MODNet. A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

PersonaLive. [CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming

hallo4. [SIGGRAPH Asia 2025] Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization

hallo3. [CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer

Awesome-Relighting.

CoRA. [CVPR 2024 & IJCV 2026] High-Quality Facial Geometry and Appearance Capture at Home.

DFEW. Python

x-nemo-inference. ICLR 2025 paper X-NeMo & Project X-Portrati2

FluxSpace. FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers [CVPR 2025]

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

EMOPortraits. Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

FEED.

SuperCLIP. Python

DNF-Avatar. [ICCV 2025 Findings Oral] DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting

PortraitRelighting. Official PyTorch implementation of the CVPR 2024 Highlight Paper "Real-time 3D-aware Portrait Video Relighting"

difareli_code. Official code for DiFaReli

DiffusionLight. [CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

One-to-All-Animation. [CVPR 2026 Poster] One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

PCNN. A Perception CNN for Facial Expression Recognition（IEEE Transactions on Image Processing 2026）

face-expressions-70k. GitHub Repository for ACM SIGGRAPH 2025 Paper: FaceExpressions-70k: A Dataset of Perceived Expression Differences

PercHead.

SHeaP. Code and models for SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians

HunyuanPortrait. [CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

precision-recall-distributions. Assessing Generative Models via Precision and Recall (official repository)

Probablistic_precision_recall. Python

SeD. Semantic-Aware Discriminator for Image Super-Resolution

mesh_align. A tool for rigid mesh alignment written in Python

DreamOmni2. This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''

QMamba. The code implementation of the paper QMamba: On First Exploration of Vision Mamba for Image Quality Assessment (ICML 2025).

Conference-Acceptance-Rate. Acceptance rates for the major AI conferences

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

Human3R. [ICLR 2026] An unified model for 4D human-scene reconstruction

gaussian-head. Official repository for TVCG 2025 paper 'GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation'

MotionRefineNet. Python

StyleGAN_for_Face_Frontalization. Identity-Preserving Face Frontalization with StyleGAN on CMU Multi-PIE

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

FlashVSR. [CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.

M3DFB. Python

Diffusion-GAN. Official PyTorch implementation for paper: Diffusion-GAN: Training GANs with Diffusion

InfiniHuman. [SIGGRAPHASIA2025] InfiniHuman: Infinite 3D Human Creation with Precise Control

Multiview-3DMM-Fitting. Fitting 3DMM models to multiview (monocular) video data.

TalkCuts. [NeurIPS 2025] TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

HRAvatar. Official implementation of the paper "HRAvatar: High-Quality and Relightable Gaussian Head Avatar" [CVPR 2025]

EHM-Tracker. Official EHM Tracking Implementation for GUAVA (ICCV 2025)

ETCH. [ICCV 2025 Highlight] ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness

MonoGaussianAvatar. Python

MPMAvatar. MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025)

pixel3dmm. [Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

Awesome-Controllable-Video-Generation. [ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

neural-deferred-shading. Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)

HuMo. HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

DH-FaceVid-1K. Official repository for the ICCV 25 paper: ​​DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation​​

SIGMAN_release. Official PyTorch implementation of SIGMAN

GSGAN. Code release for the paper "GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats"

gghead. [SIGGRAPH ASIA '24] GGHead: Fast and Generalizable 3D Gaussian Heads

Awesome-Human-Motion-Video-Generation. 【Accepted by TPAMI】Human Motion Video Generation: A Survey (https://ieeexplore.ieee.org/document/11106267)

VFHQ-downloader. VFHQ-downloader is a Python-based utility designed for the easy downloading and processing of videos from the VFHQ dataset.

RelightableAvatar. [CVPR 2024 (Highlight)] Relightable and Animatable Neural Avatar from Sparse-View Video

mvtracker. [ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking

Human-VDM. Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models

SynthMoCap. SynthMoCap Datasets

matting_human_datasets. 人像matting数据集，包含34427张图像和对应的matting结果图。

easyportrait. EasyPortrait - Face Parsing and Portrait Segmentation Dataset

SurFhead_repo. The official repo for "SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars (ICLR 2025)"

Self-Forcing-Endless. Make self forcing endless. Add cache purging. Add prompt controllability.

OpenHumanVid. [CVPR 2025] A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation

InfiniteTalk. ​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

NOVA. [ICLR 2025] Autoregressive Video Generation without Vector Quantization

ViViD. ViViD: Video Virtual Try-on using Diffusion Models

DPoser-X. [ICCV 2025 Oral] DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

SphereHead. Code Repository for Paper "SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation"

SemiUHPE. [TPAMI2025] Code for my paper "Semi-Supervised Unconstrained Head Pose Estimation in the Wild"

dinov3. Reference PyTorch implementation and models for DINOv3

RIGID. Python

SpeakerVid-5M-Code. The official SpeakerVid-5M data curation code.

FastVideo. A unified inference and post-training framework for accelerated video generation.

6dof_face. Codes and data for the TIP 2023 paper: Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image

EFHQ. Code and data for the CVPR24 paper "EFHQ: Multi-purpose ExtremePose-Face-HQ dataset" [CVPR'24]

HYPIR. Official implementation of HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration (SIGGRAPH 2025)

Tri2plane. [ECCV 2024] The repository for 'Tri$^{2}$-plane: Volumetric Avatar Reconstruction with Feature Pyramid'

op3d. Python

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

WildAvatar_Toolbox. [CVPR 2025] WildAvatar: Learning In-the-wild 3D Avatars from the Web

AnyI2V. [ICCV 2025] AnyI2V: Animating Any Conditional Image with Motion Control Generation

DAViD. Python

VolumetricSMPL. [ICCV 2025 Highlight] VolumetricSMPL

FineGym. All about FineGym (CVPR 2020 Oral): models, features, data, and more... keep starring and stay tuned!

Awesome-Video-Datasets. Video datasets

Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

GaussianAvatars. [CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"

Self-Forcing-Plus. Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

DirectMHP. [arXiv 2023.02] Codes for my paper "DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles"

C-MS-Celeb. A clean version (wash list) of MS-Celeb-1M face dataset, containing 6,464,018 face images of 94,682 celebrities

MTVCrafter. Official project page of MTVCrafter, a new paradigm for animating arbitrary characters with 4D motion tokens.

AuraFaceDetect. A quick face detection (training and inference) script using AuraFace-v1.

motionshop. Project page of replacing the human motion in the video with a virtual 3D human

seamless_interaction. Foundation Models and Data for Human-Human and Human-AI interactions.

humman_toolbox. Toolbox for HuMMan Dataset

perm. [ICLR 2025] Official implementation of "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling"

FaceLift. [ICCV 2025] FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads

Gaussian-Head-Avatar. [CVPR 2024] Official repository for "Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians"

OmniAvatar. Python

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

CameraCtrl. Python

Difix3D. [CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

difflocks. Code for our CVPR'25 paper - "DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models"

Large-Scale-Multimodal-Face-Datasets. Millions-Level Face/Human-Scene Image-Text Datasets

TeaCache. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

AnimPortrait3D. (SIGGRAPH 2025) AnimPortrait3D: Text-based Animatable 3D Avatars with Morphable Model Alignment

flux. Official inference repo for FLUX.1 models

face-3d-rotation-augmentation. Reproduction of the 3d rotation augmentation of the 300W-LP face pose data set

HAHA. HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior

ReCamMaster. [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Head360. Python

face-parsing. Real-time face parsing and facial semantic segmentation with BiSeNet - PyTorch training, ONNX export, pretrained weights.

AvatarArtist. [CVPR'25] Official PyTorch implementation of AvatarArtist: Open-Domain 4D Avatarization.

notero. A Zotero plugin for syncing items and notes into Notion

LHM. [ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds

humannorm. CVPR 2024: The official implementation of HumanNorm

change-hairstyle-ai. Get a new hairstyle in seconds.

Framework-of-GAN-Inversion. A Simplied Framework of GAN Inversion

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

Stable3DGen. A Modular Framework for 3D Generation and Beyond [WIP]

uniface. UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, recognition, parsing, gaze, attributes and anti-spoofing under one API.

head-pose-estimation. Real-time head pose estimation (yaw, pitch, roll) with ResNet and MobileNet backbones - PyTorch training and ONNX Runtime inference.

WildHead.DatProc. Data Processing for PanoHead

TalkingHead-1KH. Python

Carver. [NeurIPS'23] An efficient PyTorch-based library for training 3D-aware image synthesis models.

fractalgen. PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

R3GAN. Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.

Human3Diffusion. [NeurIPS 2024] Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models

VHAP. A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.

GnollHack. Modern evolution of the classic roguelike game NetHack

awesome-virtual-try-on. A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on.

Awesome-RWKV-in-Vision. A curated list of papers on the applications of RWKV in computer vision. Please raise an issue if you suggest new qualified project.