Houjing Huang

bravecowcow_inference_docker. Python

SlicerBraveCowCow. A 3D Slicer extension for running the inference of the 2nd Place Solution — RSNA Intracranial Aneurysm Detection locally.

GraphEnergyMatching. Official repository for "Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation"

vesselFM-CT. Segmenting all blood vessels in CT images.

ocnn-pytorch. Octree-based 3D Convolutional Neural Networks [SIGGRAPH 2017]

CADS. 🩻 Whole-body CT segmentation made simple: 22,022 scans, 167 structures, one open solution.

nnXNet. nnX-Net: An Extensible Multi-task Learning Framework for Medical Imaging

RSNA2025_Intracranial-Aneurysm-Detection. RSNA2025 Intracranial Aneurysm Detection - 2nd Place Solution

Jet-Nemotron. Python

BraTS. Providing top-performing algorithms from the Brain Tumor Segmentation (BraTS) challenges.

EnergyMatching. [NeurIPS 2025] Official repository for "Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling"

nnInteractive. nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new standard in accuracy, usability, and adaptability for clinical and research applications.

napari-nninteractive. nnInteractive plugin for Napari - nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new standard in accuracy, usability, and adaptability for clinical and research applications.

DeepIsles. Ischemic stroke segmentation tool.

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

mega-sam. Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

connected-components-3d. Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)

vesselFM. A foundation model for universal 3D blood vessel segmentation. Paper accepted @ CVPR25.

PhysRegTumor. [NeurIPS 2024] Official repository for "Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization"

ISLES22_Ensemble. MICCAI Ischemic Stroke LEsion Segmentation 2022 Top 3 Major Voting Ensemble

TNSR. Official Implementation of Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024)

syn-cerebral-octa-seg. A synthesis pipeline for annotation-free blood vessel segmentation in cerebral 3D OCTA images. Paper accepted @ MICCAI24.

transoar. A 3D medical Detection Transformer library. Papers accepted @ MIDL22 & MELBA23/02.

GliODIL. [Nature Communications 2025] Official repository for "Glioma Radiotherapy Design by Optimization of a Data and Physics Informed Discrete Loss"

GAV. A link prediction algorithm tailored to flow-driven spatial networks. Paper accepted @ WACV24.

mvpsstudio. Multiview Photometric Stereo (MVPS) Studio Hardware and Software for 3D Reconstruction

awesome-NeRF. A curated list of awesome neural radiance fields papers

implicit-shape-reconstruction. Python

TotalSegmentator. Tool for robust segmentation of >100 important anatomical structures in CT and MR images

FreeU. FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

How-Diffusion-Models-Work. In How Diffusion Models Work, you will gain a deep familiarity with the diffusion process and the models which carry it out. More than simply pulling in a pre-built model or using an API, this course will teach you to build a diffusion model from scratch.

MeViS. [ICCV 2023 & TPAMI 2025] MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

ReLA. [CVPR 2023 Highlight & IJCV 2026] GRES: Generalized Referring Expression Segmentation

Applying-DRL-to-HP-Model-for-Protein-Structure-Prediction. Source code and dataset for 2022 Publication "Applying Deep Reinforcement Learning to the HP Model for Protein Structure Prediction"

oneflow. OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Vision-Language-Transformer. [ICCV2021 & TPAMI2023] Vision-Language Transformer and Query Generation for Referring Segmentation

lost. Label Objects and Save Time (LOST) - Design your own smart Image Annotation process in a web-based environment.

genforce. An efficient PyTorch library for deep generative modeling.

Open-Edit. Code for ECCV 2020 paper "Open-Edit: Open-domain Image Manipulation with Open-Vocabulary Instructions"

uda. Unsupervised Data Augmentation (UDA)

noisystudent. Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

google-research. Google Research

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) in Python

VoV3D. Efficient 3D Backbone Network for Temporal Modeling

TransTrack. Multiple Object Tracking with Transformer

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

DALLE-pytorch. Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

awesome_OpenSetRecognition_list. A curated list of papers & resources linked to open set recognition, out-of-distribution, open set domain adaptation and open world recognition

OneNet. [ICML2021] What Makes for End-to-End Object Detection

vision_transformer. Jupyter Notebook

mmtracking. OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

former. Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)

attention-is-all-you-need-pytorch. A PyTorch implementation of the Transformer model in "Attention is All You Need".

seaborn. Statistical data visualization in Python

SETR. [CVPR 2021 & IJCV 2024] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

NLP-progress. Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

SYSU-30k. SYSU-30k Dataset of "Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark" https://arxiv.org/abs/1904.03845

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

deit. Official DeiT repository

joplin. Joplin - the privacy-focused note taking app with sync capabilities for Windows, macOS, Linux, Android and iOS.

mmpose. OpenMMLab Pose Estimation Toolbox and Benchmark.

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

CIoU. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020)

detr. End-to-End Object Detection with Transformers

shields. Concise, consistent, and legible badges in SVG and raster format

jekyll-now. Build a Jekyll blog in minutes, without touching the command line.

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

PanopticFCN. Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)

sft-reid. Implementation of "Spectral Feature Tansformation for Person Re-identification"

WeightStandardization. Standardizing weights to accelerate micro-batch training

hydra. Hydra is a framework for elegantly configuring complex applications

SingleHDR. [CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

DaNet-DensePose2SMPL. [TPAMI 2020] Learning 3D Human Shape and Pose from Dense Body Parts

MEAL-V2. MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

BA3US. code for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"

SHOT. code released for our ICML 2020 paper "Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation"

Brooklyn. 🍎 Screensaver inspired by Apple's Event on October 30, 2018

C-Plus-Plus. Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.

Python. All Algorithms implemented in Python

Relation-Aware-Global-Attention-Networks. We design an effective Relation-Aware Global Attention (RGA) module for CNNs to globally infer the attention.

SpCL. [NeurIPS-2020] Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID.

UDP-Pose. Official code of The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

TracKit. [ECCV'20] Ocean: Object-aware Anchor-Free Tracking

torchsparse. [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Graph-Optimal-Transport. Code for ICML 2020 "Graph Optimal Transport for Cross-Domain Alignment"

spconv. Spatial Sparse Convolution Library

light-reid. [ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x

ISP-reID. ISP-reID

deep-person-search. deep learning person search in PyTorch.

OpenPCDet. OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

NAE4PS. Norm-Aware Embedding for Efficient Person Search (CVPR'20)

ucasthesis. LaTeX Thesis Template for the University of Chinese Academy of Sciences

Instaboost. Code for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting"

DarkPose. Distribution-Aware Coordinate Representation for Human Pose Estimation

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

coco-annotator. :pencil2: Web-based image segmentation tool for object detection, localization, and keypoints

SOLO. SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.

deocclusion. Code for our CVPR 2020 work.

mancs. Mancs: A multi-task attentional network with curriculum sampling for person re-identification

PolarMask. Code for 'PolarMask: Single Shot Instance Segmentation with Polar Representation'

drive-cli. A command line interface for accessing google drive

caltech_pedestrian_extractor. Extract images and annotation files from the Caltech Pedestrian Dataset.

Virtual-to-Real-Pedestrian-Detection. Code and Resources for our paper "Virtual to Real adaptation of Pedestrian Detectors" - https://www.mdpi.com/1424-8220/20/18/5250

JTA-Mods. C++

DJITelloPy. DJI Tello drone python interface using the official Tello SDK. Feel free to contribute!

TelloPy. DJI Tello drone controller python package

complete-javascript-course. Starter files, final projects, and FAQ for my Complete JavaScript course

alpha-zero-gomoku. A Multi-threaded Implementation of AlphaZero (C++)

DeepReinforcementLearning. A replica of the AlphaZero methodology for deep reinforcement learning in Python

pytorch-revnet. Implementation of the reversible residual network in pytorch

AlphaZero_Gomoku. An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

gobang. javascript gobang AI，JS五子棋AI，源码+教程，基于Alpha-Beta剪枝算法（不是神经网络）

Unshaky. A software attempt to address the "double key press" issue on Apple's butterfly keyboard [not actively maintained]

resume. 个人中文简历 Latex 源码 https://hijiangtao.github.io/

stargan-v2. StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

AI_Sudoku. GUI based Smart Sudoku Solver that tries to extract a sudoku puzzle from a photo and solve it

ATSS. Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, CVPR, Oral, 2020

nasbench. NASBench: A Neural Architecture Search Dataset and Benchmark

VoVNet.pytorch. A pytorch implementation of VoVNet

imgaug. Image augmentation for machine learning experiments.

GSCNN. Gated-Shape CNN for Semantic Segmentation (ICCV 2019)

RDSNet. implement for paper: "RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation"

DCNv2. Deformable Convolutional Networks v2 with Pytorch

flops-counter.pytorch. Flops counter for neural networks in pytorch framework

robustness. Corruption and Perturbation Robustness (ICLR 2019)

augmix. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

msg-stylegan-tf. MSG StyleGAN in tensorflow

SinglePathOneShot. Python

proxylessnas. [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

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

pytorch-frn. Filter Response Normalization Layer in PyTorch

Non-local_pytorch. Implementation of Non-local Block.

BigLittleNet. Official repository for Big-Little Net

SemGCN. The Pytorch implementation for "Semantic Graph Convolutional Networks for 3D Human Pose Regression" (CVPR 2019).

darts. Differentiable architecture search for convolutional and recurrent networks

Bottom-up-Clustering-Person-Re-identification. A Bottom-Up Clustering Approach to Unsupervised Person Re-identification, AAAI 2019 (Oral)

Self-Similarity-Grouping. Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification (ICCV 2019, Oral)

ECN. Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification CVPR 2019

MAR. Pytorch code for our CVPR'19 (oral) work: Unsupervised person re-identification by soft multilabel learning

learn-regex. Learn regex the easy way

algs4. Algorithms, 4th edition textbook code and libraries

ICCV2019-LearningToPaint. ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

primitive. Reproducing images with geometric primitives.

yolact. A simple, fully convolutional model for real-time instance segmentation.

pytorch-OpCounter. Count the MACs / FLOPs of your PyTorch model.

PANet. PANet for Instance Segmentation and Object Detection

FCOS. FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Parsing-R-CNN. Parsing R-CNN for Instance-Level Human Analysis

Pose2Seg. Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

ARN. This repository is the code for ARN in CVPR 2018 workshop

Awesome-CV. :page_facing_up: Awesome CV is LaTeX template for your outstanding job application

CenterNet. Object detection, 3D detection, and pose estimation using center point detection:

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

Meta-SR-Pytorch. Meta-SR: A Magnification-Arbitrary Network for Super-Resolution (CVPR2019)

SparseMask. SparseMask: Differentiable Connectivity Learning for Dense Image Prediction.

reid-strong-baseline. Bag of Tricks and A Strong Baseline for Deep Person Re-identification

ZeroTierOne. A Smart Ethernet Switch for Earth

frp. A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

pretrained-models.pytorch. Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

senet.pytorch. PyTorch implementation of SENet

FaceSwap. Swap face between two photos.

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

FastFCN. FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation.

part_bilinear_reid. Code for ECCV2018 paper: Part-Aligned Bilinear Representations for Person Re-Identification

Learning-to-See-in-the-Dark. Learning to See in the Dark. CVPR 2018

pytorch_geometric. Graph Neural Network Library for PyTorch

SiamMask. [CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

gluon-reid. A code gallery for person re-identification with mxnet-gluon, and I will reproduce many STOA algorithm.

MGN-pytorch. Reproduction of paper: Learning Discriminative Features with Multiple Granularities for Person Re-Identification

maskscoring_rcnn. Codes for paper "Mask Scoring R-CNN".

Horizontal-Pyramid-Matching. Horizontal Pyramid Matching for Person Re-identification (AAAI 2019)

CV-arXiv-Daily. 分享计算机视觉每天的arXiv文章

Switchable-Normalization. Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779

PlotNeuralNet. Latex code for making neural networks diagrams

code-in-5. JavaScript

multi-object-tracking-paper-list. Paper list and source code for multi-object-tracking

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

experimenting-with-sort. Experimenting with sort different classical tracking algorithms for real time multiple object tracking (MOT)

toolkit. Official Python toolkit for generic object tracking benchmark GOT-10k and beyond

open-vot. Open source visual object tracking library in python

siamrpn-pytorch. A clean PyTorch implementation of SiamRPN tracker, evaluated on 7 datasets.

mot-papers. A collection of Multiple Object Tracking (MOT) papers in recent years, with notes.

deep_sort. Simple Online Realtime Tracking with a Deep Association Metric

scene_recognition. DF2Net

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

inplace_abn. In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

fast-reid. SOTA Re-identification Methods and Toolbox

CCNet. CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

PyTorch-YOLOv3. Minimal PyTorch implementation of YOLOv3

pursuit-evasion-code. Learning Evasion Strategy in Pursuit-Evasion by Deep Q-Network, ICPR2018.

handong1587.github.io. CSS

ignite. High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

pedestrian-attribute-recognition-pytorch. A simple baseline for pedestrian attribute recognition in surveillance scenarios

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

PN_GAN. Pose-Normalized Image Generation for Person Re-identification

DANet. Dual Attention Network for Scene Segmentation (CVPR2019)

PCB_RPP_for_reID. Python