周

LATO.2. Offical repo for the paper "LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow"

OpenCut. The open-source CapCut alternative

step.parts. 12,000+ open source STEP parts for your next CAD project

Syn4D. [ECCV 2026] Syn4D: A Multiview Synthetic 4D Dataset

CalMRL. [ICML 2026] Calibrated Multimodal Representation Learning with Missing Modalities

QuantClaw-plugin. QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.

PMRL. [TPAMI 2026] Principled Multimodal Representation Learning

Awesome-4D-Generation. List of papers on 4D Generation (From 2025 to now)

Silencer. [CVPR 2025] Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation

VideoCoF. [CVPR 2026 Highlight] VideoCoF: Unified Video Editing with Temporal Reasoner

ContextGen. [ICLR 2026] ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

SEED-GRPO. The official repository of SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

Awesome-Personalized-Large-Language-Models.

Awesome-Multi-Token-Prediction. A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.

LLM2Rec. [KDD'25] LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation.

soap. [SIGGRAPH'25] SOAP: Style-Omniscient Animatable Portraits

ICEdit. [NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

LIGER. Code for the paper Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection (ICLR 2025)

insert-anything. Python

GUI-R1. Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

TSGS. 🎉 Official code release of "TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors" (ACM MM 2025).

PartField. [ICCV 2025] PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

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

PE3R. [CVPR'26] PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start exploring your 3D world via text!

Guide-GRPO. Aims for memory-efficient training (24GB VRAM) on consumer GPUs. Optimizing language models through guidance tokens in reasoning chains, based on DeepSeekRL-Extended.

KEDs. Implementation of the paper Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval (CVPR 2024)

HPM. Code for "Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space"

DeltaPhi. Implementation for "DeltaPhi: Learning Physical Trajectory Residual for PDE Solving"

3DIS. [ICLR 2025 spotlight] 3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation

Hunyuan3D-1. Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

joker. Official Code Base of the Paper: "Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions"

Target-Driven-Distillation. Consistency Distillation with Target Timestep Selection and Decoupled Guidance

VillagerAgent-Minecraft-multiagent-framework. (VillagerAgent ACL 2024) A Graph based Minecraft multi agents framework

3D-Machine-Learning. A resource repository for 3D machine learning

CapHuman. [CVPR2024] CapHuman: Capture Your Moments in Parallel Universes

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

hold. [CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.

Portrait3D. (SIGGRAPH 2024) Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior

Portrait-4D. 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)

GaussianFlow. GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation (TMLR)

img2img-turbo. One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

CSMath-homeworks. Homeworks of course CSMath

StyleAvatar. Code of SIGGRAPH 2023 Conference paper: StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video

MIGC. [CVPR 2024 Highlight] MIGC and [TPAMI 2024] MIGC++ (Official Implementation)

LayerDiffuse. Transparent Image Layer Diffusion using Latent Transparency

GPAvatar. [ICLR 2024] Generalizable and Precise Head Avatar from Image(s)

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

LGM. [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

camp_zipnerf. Python

gdown. Google Drive public file downloader when curl/wget fails.

MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

4dfy. 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

LucidDreamer. Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"

Flame-PyTorch3D. Interactive render of the MPI Flame face model

MDMS. Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement (AAAI'24)

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

styleganfusion. Python

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

DreamEditor. Official code for DreamEditor: Text-Driven 3D Scene Editing with Neural Fields (Siggraph Asia 2023)

DATID-3D. [CVPR 2023] Official implementation of "DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model"

StyleGAN-nada. Python

AdaIN-style. Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

objaverse-xl. 🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

SyncDreamer. [ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

xrfeitoria. OpenXRLab Synthetic Data Rendering Toolbox

DualStyleGAN. [CVPR 2022] Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

awesome-nerf-editing. 🧙🏻‍♂️A list of papers curated for you to dive into the Awesome Radiance Field-based 3D Editing.

SegmentAnythingin3D. Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)

ffhq-dataset. Flickr-Faces-HQ Dataset (FFHQ)

TECA. Offical code of TECA: Text-Guided Generation and Editing of Compositional 3D Avatars

WhitenedCSE. [ACL2023] WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings

Awesome-Text-to-3D. A growing curation of Text-to-3D, Diffusion-to-3D works.

AnimateDiff. Official implementation of AnimateDiff.

chemnlp. ChemNLP project

Generative-AI. [TPAMI 2023] Multimodal Image Synthesis and Editing: The Generative AI Era

sam. SAM: Sharpness-Aware Minimization (PyTorch)

Drag3D. DragGAN meets GET3D for interactive mesh generation and editing.

FLAME-Universe. Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model

ActiveNeRF. Official repository of ActiveNeRF (ECCV2022)

learning_research. 本人的科研经验

nerfstudio. A collaboration friendly studio for NeRFs

threestudio. A unified framework for 3D content generation.

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

3DFuse. Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"

Fantasia3D. (ICCV 2023) official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"

SSDNeRF. [ICCV 2023] Single-Stage Diffusion NeRF

GAN-Inversion. [TPAMI 2022] GAN Inversion: A Survey

Next3D. [CVPR 2023 Highlight] Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

K-Planes. Python

blog. Public repo for HF blog posts

DiffRate. [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.

SMMix. [ICCV 23]This is a Pytorch implementation of our paper "SMMix: Self-Motivated Image Mixing for Vision Transformers"

3DDFA_V2. The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

instruct-nerf2nerf. Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)

instruct-pix2pix. Python

PanoHead. Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Make-It-3D. [ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior

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

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

StyleAvatar3D. Official repo for StyleAvatar3D

Face-Landmark-ControlNet. Proof of concept for control landmarks in diffusion models!

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

ControlNet. Let us control diffusion models!

eg3d. Python

ECON. [CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

IDE-3D. [SIGGRAPH Asia 2022] IDE-3D: Interactive Disentangled Editing For High-Resolution 3D-aware Portrait Synthesis

Fay. 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。

kapao. KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

CLIPasso. Jupyter Notebook

paper-reading. 深度学习经典、新论文逐段精读

Poseur. [ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".

DiffusionDet. [ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

Halpe-FullBody. Halpe: full body human pose estimation and human-object interaction detection dataset

retinaface. RetinaFace: Deep Face Detection Library for Python

FaRL. FaRL for Facial Representation Learning [Official, CVPR 2022]

ViTPose. 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"

vision_transformer. Jupyter Notebook

SLPT-master. Python

UniFormer. [ICLR2022] official implementation of UniFormer

MotionMixer. This is the official implementation of the paper "MotionMixer: MLP-based 3D Human Body Pose Forecasting" (IJCAI 2022, oral-presentation).

TokenPose. Implementation for : TokenPose: Learning Keypoint Tokens for Human Pose Estimation （https://arxiv.org/abs/2104.03516）. Accepted by ICCV 2021.

streamlit. Streamlit — A faster way to build and share data apps.

English-Writing. Enhance Your English Writing for Science Research 写论文英语素材

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

OFA. Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Paper-Writing-Tips. MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

awesome-tips.

MICA. MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]

torch_sampling. Efficient reservoir sampling implementation for PyTorch

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

gmm-torch. Gaussian mixture models in PyTorch.

EPro-PnP. [CVPR 2022 Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Trending-in-3D-Vision. An on-going paper list on new trends in 3D vision with deep learning

DAD-3DHeads. Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

OKDHP. [ICCV 2021] Official PyTorch Code for "Online Knowledge Distillation for Efficient Pose Estimation"

sampling-argmax. Code for "Localization with Sampling-Argmax", NeurIPS 2021

3DCommonCorruptions. 3D Common Corruptions and Data Augmentation, CVPR 2022 [Oral]

coder2gwy. 互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

insightface. State-of-the-art 2D and 3D Face Analysis Project

HeatmapInHeatmap. Official implementation of HIH:Towards More Accurate Face Alignment via Heatmap in Heatmap

FaceSynthetics. Face synthetics datasets

AHA. The project page of paper: Aha! Adaptive History-driven Attack for Decision-based Black-box Models [ICCV 2021]

BEL_regression. A code implementation for Label Encoding for Regression Networks, ICLR 2022 (spotlight).

DarkPose. Distribution-Aware Coordinate Representation for Human Pose Estimation

dsntnn. PyTorch implementation of DSNT

SingleModelUncertainty. Learning error bars for neural network predictions

ARM-Net. Pytorch implementation of our paper accepted by ECCV 2022 -- ARM: Any-Time Super-Resolution Method (https://arxiv.org/abs/2203.10812)

deterministic-uncertainty-quantification. Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"

what. Pytorch implementation of "What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?"

Generalization-Causality. 关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

SynergyNet. 3DV 2021: Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry

AGCRN. Adaptive Graph Convolutional Recurrent Network

face3d. Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.

pywt. PyWavelets - Wavelet Transforms in Python

L1-optimal-paths-Stabilization. Video Stabilization with the L1 optimal camera paths technique.

VIBE. Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

PIDOptimizer. Code for this CVPR 2018 paper: "A PID Controller Approach for Stochastic Optimization of Deep Networks", Wangpeng An, Haoqian Wang, Qingyun Sun, Jun Xu, Qionghai Dai, Lei Zhang.

xmu-daily-report. 长期维护，无需本地部署，在线fork仓库即可使用的厦大Daily Health Report 健康打卡自动填写脚本

SimCC. [ECCV'2022 Oral] PyTorch implementation for: SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation (http://arxiv.org/abs/2107.03332). Old name: SimDR

Mesh-Flow-Video-Stabilization. Online video stabilization using a novel MeshFlow motion model

awesome-video-stabilization. A curated list of video stabilization methods

torch_lfilter. bring low pass filtering to PyTorch!

FuSta. Hybrid Neural Fusion for Full-frame Video Stabilization

best_AI_papers_2021. A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.

PSS-Net. Python

landmark-detection. Four landmark detection algorithms, implemented in PyTorch.

ADOP. C++

ARFlow. The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".

sort. Simple, online, and realtime tracking of multiple objects in a video sequence.

YOLOF. You Only Look One-level Feature (YOLOF), CVPR2021, Detectron2

MCD_DA. Python

Domain-Adaptive-Faster-RCNN-PyTorch. Domain Adaptive Faster R-CNN in PyTorch

FastFlowNet. FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation (ICRA 2021)

mmflow. OpenMMLab optical flow toolbox and benchmark

DA-RetinaNet. Official Detectron2 implementation of DA-RetinaNet, An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites, Image and Vision Computing (IMAVIS) 2021

ObjectDetectionImbalance. Lists the papers related to imbalance problems in object detection [TPAMI]

imbalanced-regression. [ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

supervision-by-registration. Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

wtfpython-cn. wtfpython的中文翻译/持续🚧.../ 能力有限，欢迎帮我改进翻译

awesome-domain-adaptation. A collection of AWESOME things about domain adaptation

awesome-Face_Recognition. papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face Deblurring; Face Generation && Face Synthesis; Face Transfer; Face Anti-Spoofing; Face Retrieval;

facenet-pytorch. Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

interfacegan. [CVPR 2020] Interpreting the Latent Space of GANs for Semantic Face Editing

White-Box. Pytorch implementation of our paper accepted by IEEE TNNLS, 2022 — Carrying out CNN Channel Pruning in a White Box

awesome-productivity-cn. 绝妙的个人生产力（Awesome Productivity - Chinese version）

bdd100k. This repo has been moved to https://github.com/bdd100k/bdd100k permanently.

augmentation-corruption. This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".

AI-Job-Notes. AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）

noise. Perlin noise library for Python

procedural-advml. Task-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)

Bag-of-Tricks-for-AT. Empirical tricks for training robust models (ICLR 2021)

ttt_cifar_release. TTT Code Release

pytorch-cifar. 95.47% on CIFAR10 with PyTorch

imgclsmob. Sandbox for training deep learning networks

SA-AutoAug. Scale-aware Automatic Augmentation for Object Detection (CVPR 2021)

adversarial-frcnn. A-Fast-RCNN (CVPR 2017)

adv-training-corruptions. On the effectiveness of adversarial training against common corruptions [UAI 2022]

CVPR2024-Paper-Code-Interpretation. cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

lottery-jackpots. Pytorch implementation of our paper accepted by TPAMI 2023 — Lottery Jackpots Exist in Pre-trained Models