liutongkun

AD-Copilot. Official implementation of "AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison"

SlittingLine-Steel-Defect-Detection. Python

Explicit-Visual-Prompt. [CVPR 2023 & TPAMI 2025] Explicit Visual Prompting for Low-Level Structure Segmentations

GPT4V-for-Generic-Anomaly-Detection. [CSCWD] Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead.

awesome-anomaly-synthesis. Paper list for industrial image anomaly synthesis methods.

anomaly-detection-in-industry-manufacturing. Pipeline training and inference Anomalib models UI in Anomaly Detection

awesome-industrial-anomaly-detection. Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。

pyfqname. 用于在给定 Python 源文件与行号时，定位该行所处的类/函数作用域，并输出其模块的完全限定名（Fully Qualified Name，FQName）、类名、函数名、相对路径位置以及该行内容。

dinov3. Reference PyTorch implementation and models for DINOv3

3CAD. AAAI-2025: The largest and first anomaly detection dataset dedicated to 3C product quality control

DeepSeek-R1.

SeeGround. [CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

semseg. Semantic Segmentation in Pytorch

cat-sam. [ECCV 2024 Oral] The official implementation of "CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model".

Swin-Unet. [ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

convnext_unet. unet base on convnext aritecture

UNet-family. Paper and implementation of UNet-related model.

ConvNeXtV2-Unet. Unet-implementation based on ConvNeXtV2

BMAD. BMAD hold a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) license

Awesome-Medical-Anomaly-Detection. HTML

ocsvm-anomaly-detection. anomaly detection by one-class SVM

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

spot-diff. Project for <SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation> (ECCV 2022)

SOFS. Python

dinov3-finetune. Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

natural-synthetic-anomalies. Code for ECCV 2022 paper "Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization".

SADE. An Examination of the Compositionality of Large Generative Vision-Language Models

Dinomaly. [CVPR 2025] Official Implementation of "Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection". The first multi-class UAD model that can compete with single-class SOTAs

DADF. The official implementation of the paper DADF for industrial VAD

GLCF. Implementation for paper:"Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection"

PSP-DS. Source code and data set for the paper"Few-Shot Unseen Defect Segmentation for Polycrystalline Silicon Panels with An Interpretable Dual Subspace Attention Variational Learning Framework"

FeatUp. Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

lane-detection. Using Hough Transform to detect straight lane lines

Transformers-Tutorials. This repository contains demos I made with the Transformers library by HuggingFace.

fast_pytorch_kmeans. This is a pytorch implementation of k-means clustering algorithm

SAM-CD. Pytorch code of the SAM-CD

LayerDiffuse. Transparent Image Layer Diffusion using Latent Transparency

DFMGAN. [AAAI 2023] Official implementation of "Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation".

MSD. mobile phone screen surface defect segmentation (detection) dataset.

GC10-DET-Metallic-Surface-Defect-Datasets. This is the GC10-DET datasets of the upcoming paper " Deep Metallic Surface Defect Detection: the New Benchmark and Detection Network" The images of 10 common Metallic Surface defects were collected, and their pixel level ground-truth were labeled.

PMNet. Official code for Pixel Matching Network.

rfs. Python

SD-AANet. The code is for the paper "A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation"

DeepCrack. DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection

Stable-diffusion-defect-generation.

TGRNet-Surface-Defect-Segmentation. Code and dataset of Triplet- Graph Reasoning Network for Few-shot Metal Generic Surface Defect Segmentation

EfficientSAM. EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Few-Shot-Semantic-Segmentation-Papers. Few Shot Semantic Segmentation Papers

mixed-segdec-net-comind2021. Official PyTorch implementation for "Mixed supervision for surface-defect detection: from weakly to fully supervised learning"

Anomaly-Clustering. An unofficial implementation using Pytorch for "Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types". Improve the algorithm with DINO pretrained ViT. Implement algorithms based on PatchCore.

SA-PatchCore. Python

InsPLAD. Inspection of Power Line Assets Dataset (InsPLAD)

3DSR. Official implementation of the WACV2024 paper: Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation

osr-ood-ad-methods. This is the official repository for the paper "A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges".

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

TEASER-plusplus. A fast and robust point cloud registration library

Surface-Defect-Detection. 📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

MobileSAM. This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

Real3D-AD. [NeurIPS 2023] Offical code for <Real3D-AD: A Dataset of Point Cloud Anomaly Detection>. A 3D point cloud anomaly detection dataset and benchmark.

RD4AD. Anomaly Detection via Reverse Distillation from One-Class Embedding

CPR. This is an official implementation of the paper : "Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval" (Accepted by IEEE TIP)

antialiased-cnns. pip install antialiased-cnns to improve stability and accuracy

UnsupervisedPointCloudReconstruction. Experiments on unsupervised point cloud reconstruction.

NeAF. Code Release for AAAI 2023, "NeAF: Learning Neural Angle Fields for Point Normal Estimation"

M3DM. Python

IGR. Implicit Geometric Regularization for Learning Shapes

SCUTSurface-code. Python

ldif. 3D Shape Representation with Local Deep Implicit Functions.

patchnets. Open source repository for the code accompanying the paper 'PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations'.

NeuralTPS. Python

PredictableContextPrior. Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

NeuralPull-Pytorch. Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

points2surf. Learning Implicit Surfaces from Point Clouds (ECCV 2020)

RIAD. Reconstruction by Inpainting Based Anomaly Detection

IAE. [ICCV 2023] "Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning"

Point-MAE. [ECCV2022] Masked Autoencoders for Point Cloud Self-supervised Learning

VAND-APRIL-GAN. [CVPR 2023 Workshop] VAND Challenge: 1st Place on Zero-shot AD and 4th Place on Few-shot AD

clipseg. This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

DepthContrast. DepthContrast self-supervised learning for 3D

3d_url_survey. (TPAMI2023) Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey

AST. This is the code to the WACV 2023 paper "Asymmetric Student-Teacher Networks for Industrial Anomaly Detection" by Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn and Bastian Wandt.

3D-ADS. Official Implementation for the "Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection" paper (VAND Workshop - CVPR 2023).

Tip-Adapter. Python

AnomalyGPT. [AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

Shape-Guided. Shape-Guided Dual-Memory Learning for 3D Anomaly Detection [ICML2023]

FSS. Prototype-based Incremental Few-Shot Semantic Segmentation

REB. REB：Reducing Biases in Representation for Industrial Anomaly Detection

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

IM-IAD.

CFA_for_anomaly_localization. Python

DSR_anomaly_detection. Python

HFC. Implementation for the paper (CVPR Oral): High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

memae-anomaly-detection. MemAE for anomaly detection. -- Gong, Dong, et al. "Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection". ICCV 2019.

EfficientAD. Unofficial implementation of EfficientAD https://arxiv.org/abs/2303.14535

MNAD. An official implementation of "Learning Memory-guided Normality for Anomaly Detection" (CVPR 2020) in PyTorch.

MMR. Python

UniAD. [NeurIPS 2022 Spotlight] A Unified Model for Multi-class Anomaly Detection

elpv-dataset. A dataset of functional and defective solar cells extracted from EL images of solar modules

FAPM_official. This repository contains the implementation of FAPM (2023 ICASSP).

DRAEM. Python

houghnet. [ECCV-20] Official PyTorch implementation of HoughNet, a voting-based object detector.

Fastest_Image_Pattern_Matching. C++ implementation of a ScienceDirect paper "An accelerating cpu-based correlation-based image alignment for real-time automatic optical inspection"

shape_based_matching. try to implement halcon shape based matching, refer to machine vision algorithms and applications, page 317 3.11.5, written by halcon engineers

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

pytorch-grad-cam. Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

STEGO. Unsupervised Semantic Segmentation by Distilling Feature Correspondences

zero-shot-counting. CVPR2023 Zero-shot Counting

Deep-DIM. This is the official repo for the paper ‘’Robust Template Matching via Hierarchical Convolutional Features from a Shape Biased CNN''.

CutLER. Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

patchcore-inspection. Python

SINBAD. A method for detecting anomalies consisting of unusual combinations of normal elements using set features

Grad_CAM. Python

DownloadPaper. Python

semantic-kitti-api. SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

iris0329. Config files for my GitHub profile.

UniAD. [CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

deep-learning-for-image-processing. deep learning for image processing including classification and object-detection etc.

OpenMMLab-BoxInst. The code for OpenmmLab challenge.

anomaly-detection-resources. Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!