Deep Set Prediction Networks https://github.com/Cyanogenoid/dspn
his repository contains code for training models from the paper Burst Denoising with Kernel Prediction Networks. https://github.com/google/burst-denoising
不会用Photoshop抠图？Mask R-CNN助你一键“除”人 https://github.com/minimaxir/person-blocker
Video Crowd Counting via Dynamic Temporal Modeling https://arxiv.org/abs/1907.02198
CVPR 2019 论文开源项目合集 https://github.com/amusi/CVPR2019-Code
https://github.com/liruoteng/HeavyRainRemoval
https://github.com/nikcheerla/neuralhash
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing (AAAI 2020) https://github.com/zhilin007/FFA-Net
Code for the paper: Fighting Fake News: Image Splice Detection via Learned Self-Consistency https://github.com/minyoungg/selfconsistency
Code for our NeurIPS'19 paper "Learning Deep Bilinear Transformation for Fine-grained Image Representation" https://github.com/researchmm/DBTNet
"Self-supervised Domain adaptation for Computer Vision Tasks". https://github.com/Jiaolong/self-supervised-da
This is a Pytorch implementation of deep image blending https://arxiv.org/pdf/1910.11495.pdf https://github.com/owenzlz/DeepImageBlending
Single Image Deraining using a Recurrent Multi-scale Aggregation and Enhancement Network (ICME'19) https://github.com/nnUyi/ReMAEN
A pytorch implementation of Paper "IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis" https://github.com/hhb072/IntroVAE
This repository contains the source code for the paper First Order Motion Model for Image Animation https://github.com/AliaksandrSiarohin/first-order-model
Source code of our ACM MM 2019 paper "A New Benchmark and Approach for Fine-grained Cross-media Retrieval". https://github.com/PKU-ICST-MIPL/FGCrossNet_ACMMM2019
Code repo for "Spatio-Temporal Filter Adaptive Network for Video Deblurring" (ICCV'19) https://github.com/sczhou/STFAN
This repo contains the official training and testing codes for our paper: GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing. https://xiaohongliu.ca/GridDehazeNet/ https://github.com/proteus1991/GridDehazeNet
Code for Perspective-Guided Convolution Networks for Crowd Counting (ICCV 2019) https://github.com/Zhaoyi-Yan/PGCNet
Seeing Motion in the Dark https://github.com/cchen156/Seeing-Motion-in-the-Dark
Neural Vanishing Point Scanning via Conic Convolution https://github.com/zhou13/neurvps
High-Quality Self-Supervised Deep Image Denoising - Official TensorFlow implementation of the NeurIPS 2019 paper https://github.com/NVlabs/selfsupervised-denoising
https://github.com/weizheliu/Context-Aware-Crowd-Counting
Pytorch code for "Real image denoising with feature attention", ICCV (Oral), 2019. https://github.com/saeed-anwar/RIDNet
Doodle to Search: Practical Zero Shot Sketch Based Image Retrieval https://github.com/sounakdey/doodle2search
Codes of ECCV 2018 workshop paper "Deep Fashion Analysis with Feature Map Upsampling and Landmark-driven Attention" https://github.com/fdjingyuan/Deep-Fashion-Analysis-ECCV2018
Implementation of active contour loss function https://github.com/xuuuuuuchen/Active-Contour-Loss
Official implementation of the paper "Double-DIP: Unsupervised Image Decomposition via Coupled Deep-Image-Priors" https://github.com/yossigandelsman/DoubleDIP
https://github.com/google/tirg
Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks" https://github.com/RaphaelMeudec/deblur-gan
im2recipe: Learning Cross-modal Embeddings for Cooking Recipes and Food Images https://github.com/torralba-lab/im2recipe-Pytorch
Pytorch implementation of Neural Processes for functions and images https://github.com/EmilienDupont/neural-processes
Learning to Discover Novel Visual Categories via Deep Transfer Clustering (ICCV 2019) https://github.com/k-han/DTC
Neural 3D Mesh Renderer (CVPR 2018) https://github.com/hiroharu-kato/neural_renderer_v2
Where are the Blobs: Counting by Localization with Point Supervision https://github.com/ElementAI/LCFCN
【TEASER++：快速鲁棒的C++点云配准库】 https://github.com/MIT-SPARK/TEASER-plusplus
Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics https://github.com/ranandalon/mtl
Counting-with-Focus-for-Free https://github.com/shizenglin/Counting-with-Focus-for-Free
Pytorch Implementation of CVPR19 "Deep Stacked Multi-patch Hierarchical Network for Image Deblurring" https://github.com/HongguangZhang/DMPHN-cvpr19-master
Unsupervised Doodling and Painting with Improved SPIRAL https://learning-to-paint.github.io/
【会创造性分形、自我生长的神经细胞自动机】 https://distill.pub/2020/growing-ca/
PyTorch可视化时尚分析开源工具箱 https://github.com/open-mmlab/mmfashion
【用ASCII字符渲染3D图像】 https://github.com/alecjacobson/ascii3d
【深度学习HDR(高动态范围)图像合成文献列表】 https://github.com/vinthony/awesome-deep-hdr
https://blog.tensorflow.org/2020/01/ecovacs-robotics-ai-robotic-vacuum.html
【深度学习与AGI：计算机视觉】 https://pan.baidu.com/s/1uPids6uxa_47amZwQoTS5g
【自监督学习与计算机视觉】《Self-supervised learning and computer vision · fast.ai》 https://www.fast.ai//2020/01/13/self_supervised/
Image网 自监督学习实验 https://datasciencecastnet.home.blog/2020/02/22/self-supervised-learning-with-image%e7%bd%91/
Reference implementation of a two-level RCN model on MNIST classification. See the Science article "A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs" https://github.com/vicariousinc/science_rcn
MONAI：医学图像AI工具包 https://github.com/Project-MONAI/MONAI
基于 WebGL 的全景查看库 https://github.com/pchen66/panolens.js
【Taichi：高性能图形学编程语言】 https://github.com/taichi-dev/taichi
【图片/视频自动着色相关文献列表】 https://github.com/MarkMoHR/Awesome-Image-Colorization
【《用OpenCV4/C++开发计算机视觉项目》随书代码】 https://github.com/PacktPublishing/Building-Computer-Vision-Projects-with-OpenCV4-and-CPlusPlus
利用OpenCV和深度学习来实现人类活动识别 https://mp.weixin.qq.com/s/oPYWwZ6GkaE4L4YMxh7WGA
【(Java)实时计算机视觉库】 https://github.com/lessthanoptimal/BoofCV
【PyTorch图像恢复/去噪工具箱】’KAIR - Image Restoration Toolbox (PyTorch). Training and testing codes for DnCNN, FFDNet, SRMD, DPSR, MSRResNet, ESRGAN, IMDN'
81页计算机视觉学习指南 https://weibo.com/ttarticle/p/show?id=2309404434995602128900
Image Processing Using Multi-Code GAN Prior https://github.com/JasonGUTU/Multi-Code-GAN-Prior https://arxiv.org/abs/1912.07116
Asymmetric Generative Adversarial Networks for Image-to-Image Translation》 https://github.com/Ha0Tang/AsymmetricGAN
【图像/视频去噪算法资源集锦】 https://github.com/z-bingo/awesome-image-denoising-state-of-the-art
【图片/视频除雨相关文献资源列表】 https://github.com/nnUyi/DerainZoo
图片/视频去模糊相关资源列表 https://github.com/subeeshvasu/Awesome-Deblurring
Keras写的自驾系统 https://github.com/littlemountainman/selfdrive
【卷积网络图像质量评估】 https://github.com/idealo/image-quality-assessment
《Deep Motion Blur Removal Using Noisy/Blurry Image Pairs》 https://arxiv.org/abs/1911.08541
时尚推荐引擎：服装检索及视觉时尚推荐 https://github.com/khanhnamle1994/fashion-recommendation
https://github.com/microsoft/Microsoft-Rocket-Video-Analytics-Platform
https://github.com/cpvrlab/ImagePlay
计算机视觉入门大全：基础概念、运行原理、应用案例详解』《An Introductory Guide to Computer Vision》 https://mp.weixin.qq.com/s/uCzd5HPjSUBXGhgvhw_2Cw
图像相关、距离和分析工具包 https://github.com/CIRCL/douglas-quaid
MoGA: Searching Beyond MobileNetV3 https://github.com/xiaomi-automl/MoGA
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search https://github.com/AnnaAraslanova/FBNet
Caffe implementation of "Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval" https://github.com/chenbinghui1/Hybrid-Attention-based-Decoupled-Metric-Learning
Holocron - PyTorch implementations of recent Computer Vision tricks https://github.com/frgfm/Holocron
Official Implementation of 'Fast AutoAugment' in PyTorch. https://github.com/KakaoBrain/fast-autoaugment
通过bows (基本feature为sift)来做图像特征表示 https://github.com/lipiji/PG_BOW_DEMO
Reimplemented code for "Toward Characteristic-Preserving Image-based Virtual Try-On Network" https://github.com/sergeywong/cp-vton
计算机视觉挑战排行榜(Leaderboard)集锦 https://github.com/kobiso/Computer-Vision-Leaderboard
计算机视觉文献笔记集 https://github.com/ahong007007/Awesome_Computer_Vision
压缩自编码器有损图像压缩 https://github.com/alexandru-dinu/cae
Fastai/Pytorch Hooks/Spotify’s Annoy相似图片搜索 https://medium.com/@abhikjha/fastai-image-similarity-search-pytorch-hooks-spotifys-annoy-9161bf517aaf
斯坦福课程“计算机视觉基础与应用”课堂笔记 https://github.com/StanfordVL/CS131_notes
https://arxiv.org/abs/1907.03069
https://github.com/meteorshowers/RCF-pytorch
https://github.com/Yijunmaverick/Im2Pencil
图像质量评价指标集锦Python包 https://github.com/andrewekhalel/sewar
Implementation codes of SIGGRAPH Asia 2018 paper "Image Smoothing via Unsupervised Learning" https://github.com/fqnchina/ImageSmoothing
Progressive Image Deraining Networks: A Better and Simpler Baseline (CVPR 2019) https://github.com/csdwren/PReNet
NCNet Re-implementation on Pytorch 1.0 (Original implementation : https://github.com/ignacio-rocco/ncnet) https://github.com/XiSHEN0220/NeighConsensus
A Tensorflow implementation of RetinexNet https://github.com/weichen582/RetinexNet
This project is an unofficial implementation of AlphaGAN: Generative adversarial networks for natural image matting published at the BMVC 2018 https://github.com/CDOTAD/AlphaGAN-Matting
Code for the paper "Generalizing to Unseen Domains via Adversarial Data Augmentation", NeurIPS 2018 https://github.com/ricvolpi/generalize-unseen-domains
Tensorflow implementation of Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones (ECCV 2018 Workshop PIRM) https://github.com/Zheng222/PPCN
ECCV'18: Deep High Dynamic Range Imaging with Large Foreground Motions https://github.com/elliottwu/DeepHDR
a reimplementation of Holistically-Nested Edge Detection in PyTorch https://github.com/sniklaus/pytorch-hed
性能与OpenCV相当的轻量图像处理库(Python/C++) https://github.com/ethereon/lycon
This is the official code of spatial FCN in the paper Learning from Synthetic Data for Crowd Counting in the Wild [CVPR2019]. https://github.com/gjy3035/GCC-SFCN
故宫下雪了！我花了45秒，用Python给它画了一组手绘图 https://mp.weixin.qq.com/s/iFC0NDjMebA-5Lw6Y88sjQ
js 简单、高效的帧动画生成工具，图片处理工具 https://github.com/gkajs/gka
人像抠图 Automatic Portrait Segmentation for Image Stylization https://github.com/PetroWu/AutoPortraitMatting http://www.cse.cuhk.edu.hk/leojia/papers/portrait_eg16.pdf
道路缺陷检测 https://github.com/sekilab/RoadDamageDetector/
【Lyft感知挑战赛第四名(最快)方案】"Lyft Perception Challenge | Self-Driving Cars Lab" https://github.com/NikolasEnt/Lyft-Perception-Challenge
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift https://github.com/google/quickshift
快速图像增广库 https://github.com/albu/albumentations
用OpenCV实现活体检测 https://www.pyimagesearch.com/2019/03/11/liveness-detection-with-opencv/
将涂鸦生成逼真照片：空间自适应归一化语义图像合成 https://nvlabs.github.io/SPADE/ https://github.com/NVlabs/SPADE
Facebook开源2D图片实时3D姿态估计DensePose(Caffe2) https://github.com/facebookresearch/DensePose
快速图像增广库 https://github.com/albu/albumentations
深度学习表征不可思议有效性——相似图像搜索实践 https://github.com/hundredblocks/semantic-search
由文本生成人脸图像 —— T2F https://github.com/akanimax/T2F
Attentive Generative Adversarial Network for Raindrop Removal from a Single Image（雨点去除） https://github.com/rui1996/DeRaindrop
单图去雨 https://github.com/XiaLiPKU/RESCAN
全局上下文场景图解析 https://github.com/rowanz/neural-motifs
用预训练模型从标记数据集创建操纵向量(例如将头发颜色改为红色)，可在本地运行的Demo，制作自己的微笑视频 https://github.com/openai/glow
用TensorFlow Lite实现快速肖像分割 https://hyperconnect.github.io/2018/07/06/tips-for-building-fast-portrait-segmentation-network-with-tensorflow-lite.html
Repulsion Loss: Detecting Pedestrians in a Crowd 群体中的行人识别（修改loss函数） https://github.com/bailvwangzi/repulsion_loss_ssd
Fast and Accurate Online Video Object Segmentation via Tracking Parts 跟踪 https://github.com/JingchunCheng/FAVOS
Detect-and-Track高效视频人体姿态估计 https://github.com/facebookresearch/DetectAndTrack
Adaptive Temporal Encoding Network for Video Instance-level Human Parsing https://github.com/HCPLab-SYSU/ATEN
压缩视频高性能行为识别 https://github.com/chaoyuaw/pytorch-coviar
Repository for Scale-recurrent Network for Deep Image Deblurring http://www.xtao.website/projects/srnd… https://github.com/jiangsutx/SRN-Deblur
Decomposing an input image into layers via "color unblending" https://koyama.xyz/project/color_unbl… https://github.com/yuki-koyama/unblending
Hierarchy-based Image Embeddings for Semantic Image Retrieval https://github.com/cvjena/semantic-embeddings
reference: https://arxiv.org/pdf/1612.06321.pdf https://github.com/nashory/DeLF-pytorch
https://github.com/hzwer/LearningToPaint https://zhuanlan.zhihu.com/p/61761901
iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection 人的交互识别 https://github.com/vt-vl-lab/iCAN
Light-Head R-CNN: In Defense of Two-Stage Object Detector https://github.com/zengarden/light_head_rcnn
You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery https://github.com/CosmiQ/yolt
关键点对目标检测 https://github.com/umich-vl/CornerNet
CVPR 2018/ECCV 2018姿态估计相关工作汇总 https://github.com/wjbKimberly/pose_estimation_CVPR_ECCV_2018
A Deep Learning based project for colorizing and restoring old images https://github.com/jantic/DeOldify
人群计数相关资源列表 https://github.com/gjy3035/Awesome-Crowd-Counting
Joint Body Parsing & Pose Estimation Network https://github.com/Engineering-Course/LIP_JPPNet
Python开源图像处理框架ImagePy，其UI界面支持开放插件 https://github.com/Image-Py/imagepy
Image Super-Resolution Using Very Deep Residual Channel Attention Networks https://github.com/yulunzhang/RCAN
On The Effectiveness Of Visible Watermarks https://github.com/rohitrango/automatic-watermark-detection
Python/OpenCV图像拼接 https://www.pyimagesearch.com/2018/12/17/image-stitching-with-opencv-and-python/
显微镜图像细胞计数工具包 https://github.com/hammerlab/cytokit
用相片创建生动有趣的马赛克图片 https://github.com/worldveil/photomosaic
JPEG压缩感知：直接利用DCT域特征的高效神经网络图片识别 https://eng.uber.com/neural-networks-jpeg/
Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software https://github.com/satoshi-kosugi/Unpaired-Image-Enhancement
Collaging on Internal Representations: An Intuitive Approach for Semantic Transfiguration https://github.com/quolc/neural-collage
Replacing Mobile Camera ISP with a Single Deep Learning Model RAW to RGB 图像数据集(22G) http://people.ee.ethz.ch/~ihnatova/pynet.html
An implementation of paper "Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning" (CVPR19)
模拟生成雨景图片，CGAN恢复 https://github.com/liruoteng/HeavyRainRemoval
https://github.com/hellloxiaotian/ADNet
Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS, 2019) (Pytorch) https://github.com/zsyOAOA/VDNet
Single-Underwater-Image-Enhancement-and-Color-Restoration https://github.com/wangyanckxx/Single-Underwater-Image-Enhancement-and-Color-Restoration
https://github.com/ethliup/SelfDeblur
【图片匹配挑战2020】’Image Matching Benchmark - Public release of the Image Matching Benchmark' https://github.com/vcg-uvic/image-matching-benchmark
深度学习(图像)数据增广库 https://github.com/MIPT-Oulu/solt
用AutoAugment自学习数据增广改进深度学习性能 https://github.com/tensorflow/models/tree/master/research/autoaugment
Integral Human Pose Regression https://github.com/JimmySuen/integral-human-pose
(Python)图像哈希库 https://github.com/JohannesBuchner/imagehash
Learning to cluster in order to transfer across domains and tasks https://github.com/GT-RIPL/L2C
Mixup数据增广技术(fastai)(CIFAR-10, 1 GPU, 94% accuracy, 6 minutes) https://forums.fast.ai/t/mixup-data-augmentation/22764
快速图像增广库 https://github.com/albu/albumentations
PyTorch implementation of "Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer" https://github.com/oripress/ContentDisentanglement
Video Compression through Image Interpolation (ECCV'18) [PyTorch] https://github.com/chaoyuaw/pytorch-vcii
动漫人物图片自动修复，去马赛克，填补，去瑕疵 https://github.com/youyuge34/Anime-InPainting
OpenCV图像处理入门100题实例解析 https://github.com/yoyoyo-yo/Gasyori100knock
-
椭圆检测 cvpr matlab https://github.com/AlanLuSun/High-quality-ellipse-detection https://www.52cv.net/?p=1535
-
英特尔重磅开源OpenVINO™ ！附送的预训练模型是最大亮点 非常强大！！！ https://www.52cv.net/?p=1550 https://github.com/opencv/dldt https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models
基于改进版OpenTLD和RNet的人脸追踪 https://github.com/HandsomeHans/Face-Tracking-Based-on-OpenTLD-and-RNet
C++实现的自动全景拼接 https://github.com/ppwwyyxx/OpenPano
Code Release for LF-Net: Learning Local Features from Images https://github.com/vcg-uvic/lf-net-release
Deep Learning for Anomaly Detection: A Survey https://arxiv.org/abs/1901.03407
Delira：医疗图像(放射学)轻量深度学习框架 https://github.com/justusschock/delira
Quickly search over billions of images https://github.com/EdjoLabs/image-match
Squoosh 是 Google 推出的一款在线简单高效的图片压缩工具，支持 JPG、PNG 和 WebP 格式 https://github.com/GoogleChromeLabs/squoosh
最新的边缘检测和图像过分割 https://mmcheng.net/zh/rcfedge/
【C++实时视觉跟踪包】’OpenTracker - Real-time C++ ECO tracker etc. speed-up by SSE/NEON, support Linux, Mac, Jetson TX1/2, raspberry pi https://github.com/rockkingjy/OpenTracker
Intel的开源图像(渲染)去噪库 https://github.com/OpenImageDenoise/oidn
Visualizing Deep Similarity Networks https://github.com/GWUvision/Similarity-Visualization
基于ImageNet-1k的图像分类模型集 https://github.com/osmr/imgclsmob Sandbox for training convolutional networks for computer vision
利用深度学习，在手机上拍出单反相机效果的照片，Make your pictures beautiful with a touch of deep learning magic http://people.ee.ethz.ch/~ihnatova/ https://github.com/aiff22/DPED
如何将人脸与卡通动物脸融合并将其做成一项业务 https://medium.com/m/global-identity?redirectUrl=https%3A%2F%2Fhackernoon.com%2Fhow-we-used-ai-to-hybridize-humans-with-cartoon-animals-and-made-a-business-out-of-it-2d3ec9368ceb
CNN运动模糊检测 https://github.com/Sibozhu/MotionBlur-detection-by-CNN
Learning Deep CNN Denoiser Prior for Image Restoration (CVPR, 2017) https://github.com/cszn/ircnn
边缘检测文献大列表 https://github.com/MarkMoHR/Awesome-Edge-Detection-Papers
黄图鉴别(不可描述图片检测) https://github.com/rockyzhengwu/nsfw
Monk：OpenCV/深度学习开源GUI工具 https://github.com/Tessellate-Imaging/monk_v1
图像配准：从SIFT到深度学习 https://medium.com/m/global-identity?redirectUrl=https%3A%2F%2Fblog.sicara.com%2Fimage-registration-sift-deep-learning-3c794d794b7a
将文件隐写进图片文件 https://github.com/DimitarPetrov/stegify
医学影像交互工具包 https://github.com/MITK/MITK
https://github.com/aosokin/os2d
Synthesizing human-like sketches from natural images using a conditional convolutional decoder https://github.com/kampelmuehler/synthesizing_human_like_sketches
TideFinger——指纹识别小工具，汲取整合了多个web指纹库，结合了多种指纹检测方法，让指纹检测更快捷、准确 https://github.com/TideSec/TideFinger
EnlightenGAN: Deep Light Enhancement without Paired Supervision https://github.com/yueruchen/EnlightenGAN
Code repo for "DAVANet: Stereo Deblurring with View Aggregation" (CVPR'19, Oral) https://github.com/sczhou/DAVANet
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising (TIP, 2018) https://github.com/cszn/FFDNet
The code for the CVPR2019 paper Bi-Directional Cascade Network for Perceptual Edge Detection https://github.com/pkuCactus/BDCN
用深度学习和局部敏感哈希搜索相似图片 https://towardsdatascience.com/finding-similar-images-using-deep-learning-and-locality-sensitive-hashing-9528afee02f5
https://github.com/Ir1d/image-processing-datasets
【照片/图片自动着色】’DeOldify - Colorise Anime/Manga Sketches with DeOldify' https://github.com/Dakini/AnimeColorDeOldify
AiThermometer：用热成像仪自动测量人体温度 https://github.com/IIT-PAVIS/AI-Thermometer
RANSAC-Flow: generic two-stage image alignment https://github.com/XiSHEN0220/RANSAC-Flow
拍照隔着玻璃窗？铁丝网？试试一键穿透——"障碍穿透视觉学习" https://colab.research.google.com/drive/1iOKknc0dePekUH2TEh28EhcRPCS1mgwz
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline https://github.com/alex04072000/SingleHDR
Self-Supervised Viewpoint Learning From Image Collections https://github.com/NVlabs/SSV
SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects https://www.arxiv-vanity.com/papers/2004.04977/
https://github.com/LingDong-/skeleton-tracing
SIFT简洁明了的Python实现 https://github.com/rmislam/PythonSIFT
PyTorch图像检索工具箱 PyRetri https://github.com/PyRetri/PyRetri
'ScreenPoint - Project an image centroid to another image using OpenCV' https://github.com/cyrildiagne/screenpoint
一文讲解图像插值算法原理！附Python实现！ https://mp.weixin.qq.com/s/EFJEhFAVXRmfrDysVAGeQw
Visual Perception Model for Rapid and Adaptive Low-light Image Enhancement https://github.com/MDLW/Low-Light-Image-Enhancement https://www.arxiv-vanity.com/papers/2005.07343/
【线稿自动着色】’Automatic Line Art Colorization - Automatic line art colorization using various types of hint or without hint' https://github.com/SerialLain3170/Colorization
Attention-based network for low-light image enhancement https://www.arxiv-vanity.com/papers/2005.09829/
【Facebook将最新CV技术用于提供购物新体验】《Powered by AI: Advancing product understanding and building new shopping experiences》 https://ai.facebook.com/blog/powered-by-ai-advancing-product-understanding-and-building-new-shopping-experiences
*《Instance-aware Image Colorization》 https://github.com/ericsujw/InstColorization
《Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering》 https://www.arxiv-vanity.com/papers/2005.13131/
一位来自得克萨斯州的软件艺术家 Everest Pipkin 在 GitHub 上开源了一款工具：Image Scrubber。该工具可快速移除图像中的元数据（EXIF 数据）识别信息，实现局部关键位置的打码操作，以保障图像发布者的隐私安全。 https://github.com/everestpipkin/image-scrubber
【涂鸦应用相关文献大列表】’Awesome-Sketch-Based-Applications - 📚 A collection of sketch based application papers.' https://github.com/MarkMoHR/Awesome-Sketch-Based-Applications
Foreground-aware Semantic Representations for Image Harmonization https://github.com/saic-vul/image_harmonization
【遗传算法辅助画画】’Genetic Drawing - A genetic algorithm toy project for drawing' https://github.com/anopara/genetic-drawing
【非深度学习方法天空检测器】“Sky-Area-Detector - sky area detection without deep neural networks” https://github.com/MaybeShewill-CV/sky-detector
【曲线检测器】《Curve Detectors | Distill》 https://distill.pub/2020/circuits/curve-detectors/
单幅图片HDR重建 paper:《Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline》 https://github.com/alex04072000/SingleHDR
pulse。可借助 AI 手段让一些模糊图像顿时变得清晰起来，即使图片被打上马赛克，也能生成（不是还原）高清无码图。 https://github.com/adamian98/pulse
'CV_interviews_Q-A - CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理和 C++基础四大块' https://github.com/GYee/CV_interviews_Q-A
【(图片/视频)除雾文献/数据集/代码列表】 https://github.com/cxtalk/DehazeZoo
EyeLoop：开源Python眼动追踪器，专为消费级硬件上的动态闭环实验定制 https://github.com/simonarvin/eyeloop
基于opencv+UIAutomator 的公主连结农场脚本，使用opencv图像识别进行按钮分析 https://github.com/SimonShi1994/Princess-connection-farm
《用 Python 写一个 JPEG 解码器》 https://yasoob.me/posts/understanding-and-writing-jpeg-decoder-in-python/
【用Python代码理解和解码JPEG图像】 https://yasoob.me/posts/understanding-and-writing-jpeg-decoder-in-python/
DeepCreamPy 是一个借助深度神经网络去掉二次元图片中的马赛克的工具。 https://github.com/deeppomf/DeepCreamPy
【sherloq：开源数字图像取证工具集】’sherloq - An open-source digital image forensic toolset' https://github.com/GuidoBartoli/sherloq
【(PyTorch)基于DeViSe视觉语义潜入的反向图像检索实战】 https://medium.com/@vijayabhaskar96/fun-project-devise-on-pytorch-83eb09694d41
【基于OpenCV的机读答题卡识别】 https://github.com/Muhammad-Yunus/OpenCV-LJK-Checker
Generative Hierarchical Features from Synthesizing Images https://github.com/genforce/ghfeat
【GG-AESY：图片加密信息隐写工具】 https://github.com/jfmaes/GG-AESY
[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline https://github.com/alex04072000/SingleHDR
Perceptual Optimization of Image Quality Assessment (IQA) Models https://github.com/dingkeyan93/IQA-optimization
[CVPR 2020] Instance-aware Image Colorization https://github.com/ericsujw/InstColorization
This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis" https://github.com/Rudrabha/Lip2Wav
Syn2Real Transfer Learning for Image Deraining using Gaussian Processes https://github.com/rajeevyasarla/Syn2Real
AdaLAM is a fully handcrafted realtime outlier filter integrating several best practices into a single efficient and effective framework. It detects inliers by searching for significant local affine patterns in image correspondences. https://github.com/cavalli1234/AdaLAM
Code and information for face image quality assessment with SER-FIQ https://github.com/pterhoer/FaceImageQuality
Implementation of paper which uses a swish-gated residual U-net to color line-art anime drawings https://github.com/pradeeplam/Anime-Sketch-Coloring-with-Swish-Gated-Residual-UNet
https://github.com/hongwang01/RCDNet
This repository implements Deferred Neural Rendering: Image Synthesis using Neural Textures . https://github.com/SSRSGJYD/NeuralTexture
https://github.com/youngkyunJang/GPQ
Don't Hit Me! Glass Detection in Real-world Scenes https://github.com/Mhaiyang/CVPR2020_GDNet
LISRD - Local Invariance Selection at Runtime for Descriptors https://github.com/rpautrat/LISRD
official implementation of the spatial-temporal attention neural network (STANet) for remote sensing image change detection https://github.com/justchenhao/STANet
PyTorch code for "SOLAR: Second-Order Loss and Attention for Image Retrieval". In ECCV 2020 https://github.com/tonyngjichun/SOLAR
Unpaired Learning of Deep Image Denoising https://github.com/XHWXD/DBSN
Pytorch code for "Spatial-Adaptive Network for Single Image Denoising" https://github.com/JimmyChame/SADNet
Code for paper "Deep Hough Transform for Semantic Line Detection" (ECCV2020) https://github.com/Hanqer/deep-hough-transform
Code for the CVPR 2020 paper "A Multi-task Mean Teacher for Semi-supervised Shadow Detection" https://github.com/eraserNut/MTMT
Tensorflow Implementation of DexiNed for Edge Detection https://github.com/xavysp/DexiNed
https://github.com/OPHoperHPO/image-background-remove-tool
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement https://github.com/Li-Chongyi/Zero-DCE
Fast underwater image enhancement for Improved Visual Perception. https://github.com/xahidbuffon/funie-gan
Repository for Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms https://github.com/rimchang/RealBlur
LineNormalizer：基于深度学习的漫画线稿线宽归一化 https://github.com/hepesu/LineNormalizer
新书稿：《计算机视觉：算法与应用(第二版)》 http://szeliski.org/Book/
图像/视频去噪文献代码列表 https://github.com/oneTaken/Awesome-Denoise
涂鸦(草图)相关研究/文献列表 https://github.com/qyzdao/Sketch-Based-Deep-Learning
视频/图片去雨🌧️相关文献大列表 https://github.com/hongwang01/Video-and-Single-Image-Deraining
cv::ximgproc::FastLineDetectors是opencv-contrib中用于检测直线的模块，该方法能在较短时间内获得精度较高的直线检测结果，且不需要调节参数。该函数是LineSegmentDetector因版权问题从opencv中移除后最易用的直线检测小能手 https://livezingy.com/fastlinedetectors-opencv-contrib/
视觉语义嵌入/文本-图像检索文献列表 https://github.com/hardyqr/Visual-Semantic-Embeddings-an-incomplete-list
机器学习与艺术：创意案例集 https://mlart.co/
https://github.com/danielgatis/rembg
SORT：简单开源光线追踪器 https://github.com/JiayinCao/SORT
Creative Sketch Generation (DoodlerGAN)：创造性涂鸦生成 https://github.com/facebookresearch/DoodlerGAN
Awesome-CVPR2020-Low-Level-Vision：汇总了下CVPR 2020图像重建(Image Reconstruction)/底层视觉(Low-Level Vision)相关的一些论文，包括超分辨率，图像恢复，去雨，去雾，去模糊，去噪等方向 https://github.com/Kobaayyy/Awesome-CVPR2020-Low-Level-Vision
Caer - 面向高性能AI研究的轻量计算机视觉库，支持GPU，可替代OpenCV https://github.com/jasmcaus/caer
https://github.com/ocampor/image-quality
PyTorch图像质量评价包 https://github.com/francois-rozet/piqa
CVPODS：面向多种计算机视觉任务的多功能代码库：分类，分割，检测，自监督学习，关键点和3D 等 https://github.com/Megvii-BaseDetection/cvpods
pre-Trained Image Processing Transformer https://arxiv.org/abs/2012.00364
MIRNet-TFJS：TensorFlow JS实现的用于低照度图片增强的MIRNet模型 https://github.com/Rishit-dagli/MIRNet-TFJS
创造性机器学习艺术作品和项目集 https://mlart.co/
2020十大热门计算机视觉论文及其演示与代码 https://github.com/louisfb01/Top-10-Computer-Vision-Papers-2020
https://github.com/volotat/DiffMorph
https://github.com/nihui/opencv-mobile
Glasses：高质量计算机视觉深度学习库 https://github.com/FrancescoSaverioZuppichini/glasses
深度学习图像去噪 https://medium.com/towards-artificial-intelligence/image-de-noising-using-deep-learning-1a8334c81f06
Python卫星图像分析综合指南 https://towardsdatascience.com/comprehensive-guide-to-satellite-imagery-analysis-using-python-1b4153bad2a
用DeepFashion和Fastai实现深度服装分类 https://towardsdatascience.com/clothes-classification-with-the-deepfashion-dataset-and-fast-ai-1e174cbf0cdc
Multi-Stage Progressive Image Restoration https://github.com/swz30/MPRNet
SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning https://github.com/tsujuifu/pytorch_sscr
Multi-Scale Progressive Fusion Network for Single Image Deraining (MSPFN) https://github.com/kuijiang0802/MSPFN
Domain Adaptation for Image Dehazing, CVPR2020 https://github.com/HUSTSYJ/DA_dahazing
Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring (ECCV2020 Spotlight) https://github.com/zzh-tech/ESTRNN
The implementation of "Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance". https://github.com/liyucs/RAGNet
https://github.com/cvlab-stonybrook/DM-Count
This repository shows the TensorFlow Lite and TensorRT model conversion and inference processes for the MIRNet model as proposed by Learning Enriched Features for Real Image Restoration and Enhancement. https://github.com/sayakpaul/MIRNet-TFLite-TRT
we propose EfficientDerain for high-efficiency single-image deraining https://github.com/tsingqguo/efficientderain
Rain Rendering for Evaluating and Improving Robustness to Bad Weather (Tremblay et al., 2020) https://github.com/cv-rits/rain-rendering
Learning from Synthetic Shadows for Shadow Detection and Removal https://github.com/naoto0804/SynShadow
Code for the ICPR 2020 paper: "CURL: Neural Curve Layers for Image Enhancement" https://github.com/sjmoran/CURL
HardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing https://github.com/huangzilingcv/HardGAN
Keras Implementation of the paper Deep HDR Imaging via A Non-Local Network - TIP 2020 https://github.com/tuvovan/NHDRRNet
Beyond Brightening Low-light Images https://github.com/zhangyhuaee/KinD_plus
ImageStore：Google Photos的开源实现，用Docker部署 https://github.com/gregordr/ImageStore
图像质量评价算法列表 https://github.com/weizhou-geek/Image-Quality-Assessment-Benchmark
Deep Illuminator：基于深度学习的图片重打光增强工具 https://github.com/chogovadze/Deep-Illuminator
PyTorch code for the CVPR'20 paper "Learning Better Lossless Compression Using Lossy Compression" https://github.com/fab-jul/RC-PyTorch
BEBLID: Boosted Efficient Binary Local Image Descriptor https://github.com/iago-suarez/BEBLID
pierogis：Python图像/动画处理框架 https://github.com/pierogis/pierogis
Awesome Low-light Enhancement：低光照图像增强相关文献资源列表 https://github.com/Elin24/Awesome-Low-Light-Enhancement
免费书：从零开始学计算机图形学 https://gabrielgambetta.com/computer-graphics-from-scratch/
Alto：DIY视觉识别小机器人 https://github.com/googlecreativelab/alto
Official PyTorch implementation of "Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss" (SIGGRAPH 2020) https://github.com/marcelsan/Deep-HdrReconstruction
彩色图像生成素描图像 2020.12 Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale https://arxiv.org/abs/2012.09004 https://github.com/TZYSJTU/Sketch-Generation-with-Drawing-Process-Guided-by-Vector-Flow-and-Grayscale
U^2-Net肖像画生成 https://github.com/NathanUA/U-2-Net
将真实图像转换为日漫风格的画作 https://github.com/TachibanaYoshino/AnimeGAN
简单照片卡通化serverless机器学习App的创建与部署实例 https://github.com/ahmedbesbes/cartoonify
2012.5 Real-time Image Smoothing via Iterative Least Squares https://arxiv.org/abs/2003.07504 https://github.com/wliusjtu/Real-time-Image-Smoothing-via-Iterative-Least-Squares matlab代码，可借鉴思想作为评判生成图像好坏的依据
Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image https://github.com/scut-mingqinchen/self2self
Auto-exposure Fusion for Single-image Shadow Removal》(CVPR 2021) https://github.com/tsingqguo/exposure-fusion-shadow-removal
JdeRobot Academy: 通过实践学习机器人和计算机视觉 https://github.com/JdeRobot/RoboticsAcademy
《DeFMO: Deblurring and Shape Recovery of Fast Moving Objects》(CVPR 2021) https://github.com/rozumden/DeFMO
【MMEditing：图像/视频编辑工具箱】 github.com/open-mmlab/mmediting
《Back to the Feature: Learning Robust Camera Localization from Pixels to Pose》(CVPR 2021) github.com/cvg/pixloc
《Uncertainty-aware blind image quality assessment in the laboratory and wild 》(2020) github.com/zwx8981/UNIQUE
Monster Mash：基于草图的3D随意建模与动画工具 github.com/google/monster-mash
xxYUV：C/C++写的高性能RGB<->YUV转换库 github.com/metarutaiga/xxYUV
《Deblurring using Analysis-Synthesis Networks Pair》(CVPR 2020) github.com/adamkau/analysis-synthesis-deblurring
《Single Image Reflection Removal Beyond Linearity》(CVPR 2019) github.com/csqiangwen/Single-Image-Reflection-Removal-Beyond-Linearity
《ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis》(CVPR 2021) github.com/yinanhe/ForgeryNet
triangula：三角化图像生成器 github.com/RH12503/triangula
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition (CVPR 2021) github.com/Megvii-BaseDetection/DisAlign
几何深度学习 https://www.arxiv-vanity.com/papers/2104.13478/
《计算机视觉机器学习实战》随书源码 github.com/GoogleCloudPlatform/practical-ml-vision-book
Image-Contrast-Enhancement：多种图像对比度增强技术的C++实现 github.com/dengyueyun666/Image-Contrast-Enhancement
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding github.com/microsoft/vision-longformer
《Deep Convolutional Dictionary Learning for Image Denoising》(CVPR 2021) github.com/natezhenghy/DCDicL_denoising
《Code for Region-Adaptive Deformable Network for Image Quality Assessment》(CVPRW 2021) github.com/IIGROUP/RADN
《Deep Vectorization of Technical Drawings》(ECCV 2020) github.com/Vahe1994/Deep-Vectorization-of-Technical-DrawingsVisionLongformerForObjectDetection
《Recurrent Multi-Frame Deraining: Combining Physics Guidance and Adversarial Learning》(2021) github.com/flyywh/Recurrent-Multi-Frame-Deraining
《Self-Learned Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence》(CVPR 2020) github.com/flyywh/CVPR-2020-Self-Rain-Removal
《A Unified End-to-End Framework for Efficient Deep Image Compression》(2020) github.com/liujiaheng/compression
pyVHR：Python实现的rPPG虚拟心律检测框架 github.com/phuselab/pyVHR
《General Virtual Sketching Framework for Vector Line Art》(SIGGRAPH 2021) github.com/MarkMoHR/virtual_sketching
《计算机视觉实战演练：算法与应用》中文电子书 github.com/Charmve/computer-vision-in-action
EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration github.com/zeyuxiao1997/EDPN
github.com/sel118/LaneAF
计算机视觉实战演练：算法与应用，作者为迈微 AI 研习社创始人、CSDN 博客专家。 本书大致分为三部分： 一：计算机视觉相关的基础知识和预备知识； 二：计算机视觉基础理论（核心部分为神经网络模型）； 三：常见模型介绍，如：Transformer、Attention、知识蒸馏、迁移学习、生成对抗模型等。 github.com/Charmve/computer-vision-in-action
Image Quality Assessment Toolbox：图像质量评估工具箱 github.com/RyanXingQL/Image-Quality-Assessment-Toolbox
Learning to Predict Visual Attributes in the Wild https://www.arxiv-vanity.com/papers/2106.09707
Recognizing one-dimensional barcode using OpenCV https://opencv.org/recognizing-one-dimensional-barcode-using-opencv/
https://ai.googleblog.com/2021/06/take-all-your-pictures-to-cleaners-with.html
HuggingPics：用网络图片微调视觉Transformer github.com/nateraw/huggingpics
OpenCV教程应用程序的源代码 github.com/JimmyHHua/opencv_tutorials
基于卫星图像的非洲建筑分布图绘制 https://ai.googleblog.com/2021/07/mapping-africas-buildings-with.html https://arxiv.org/abs/2107.12283
Self-supervised Multisensor Change Detection https://arxiv.org/abs/2103.05102
MUSIQ: Multi-scale Image Quality Transformer github.com/google-research/google-research/tree/master/musiq
WaterDetect：端到端水文检测算法 github.com/cordmaur/WaterDetect
PaddlePaddle Vision Transformers：PaddlePaddle视觉Transformer(ViT)/MLP模型库 github.com/BR-IDL/PaddleViT
HugsVision：易用的huggingface封装库，可轻松开发最先进计算机视觉技术，包括图像分类、语义分割、目标检测分析、图像生成、去噪等 github.com/qanastek/HugsVision
Keras实例：MIRNet低光照图像增强 https://keras.io/examples/vision/mirnet/
里面主要整理了作者在研究生期间的学习内容，教程将以视频的内容呈现，主要介绍网络结构与创新点、基于 PyTorch / TensorFlow 搭建与训练网络。 github.com/WZMIAOMIAO/deep-learning-for-image-processing
OpenCV教程应用程序的源代码 github.com/JimmyHHua/opencv_tutorials
神经(网络)渲染相关资源大列表 github.com/zzw-zwzhang/Awesome-of-Neural-Rendering
Towards Flexible Blind JPEG Artifacts Removal github.com/jiaxi-jiang/FBCNN
ICCV 2021图像生成(Image Generation)和底层视觉(Low-Level Vision)任务相关的论文和代码，包括图像生成，图像编辑，图像风格迁移，图像翻译，图像修复，图像超分及其他底层视觉任务 github.com/Kobaayyy/Awesome-ICCV2021-Low-Level-Vision
【CVNets: 计算机视觉网络训练库】 github.com/apple/ml-cvnets
LearningToCountEverything目标自动计数 github.com/Kazuhito00/LearningToCountEverything-Colaboratory-Sample
https://arthurdouillard.com/deepcourse/ https:// github.com/arthurdouillard/deepcourse
Latent Diffusion Models：基于潜扩散模型的高分辨率图像合成模型集 github.com/CompVis/latent-diffusion
QRCode-NCNN：ncnn移植版二维码识别引擎 github.com/EdVince/QRCode-NCNN
Dense Extreme Inception Network for Edge Detection https://arxiv.org/abs/2112.02250
Deep Image Deblurring: A Survey https://arxiv.org/abs/2201.10700
github.com/WZMIAOMIAO/deep-learning-for-image-processing
Gyroflow：基于陀螺仪数据的视频画面稳定器 github.com/gyroflow/gyroflow
LEDNet: Joint Low-light Enhancement and Deblurring in the Dark https://arxiv.org/abs/2202.03373
FAST：基于GPU的高性能医学图像处理与可视化框架 github.com/smistad/FAST
CLIPasso: Semantically-Aware Object Sketching https://arxiv.org/abs/2202.05822
Hugging Face教学资源包 https://huggingface2.notion.site/Education-Toolkit-7b4a9a9d65ee4a6eb16178ec2a4f3599
Awesome-Image-Matting：抠图相关工作列表 github.com/michaelowenliu/awesome-image-matting
Pydrawing：图片/视频美化工具包 github.com/CharlesPikachu/pydrawing
IQA-PyTorch：PyTorch图像质量评估工具箱 github.com/chaofengc/IQA-PyTorch
阴影去除文献资源集 github.com/GuoLanqing/Awesome-Shadow-Removal
cisip-FIRe：快速图像搜索引擎 github.com/CISiPLab/cisip-FIRe
github.com/deepbands/buildseg
使用深度网络恢复和归因古文字 github.com/deepmind/ithaca
Leveraging Self-Supervision for Cross-Domain Crowd Counting https://arxiv.org/abs/2103.16291
github.com/PaddleCV-SIG/PaddleRS https://wx2.sinaimg.cn/mw690/5396ee05ly1h09pkisdrnj21dy0oq4qp.jpg
Cell-ACDC：基于Python GUI的框架，用于细胞成像数据的分割、跟踪和细胞周期标注 github.com/SchmollerLab/Cell_ACDC https://wx2.sinaimg.cn/mw690/5396ee05ly1h09oxvqpnwj21qc1gi4qp.jpg
Graphite：开源跨平台数字图像(光栅/矢量)编辑器，用于2D图形编辑、照片处理、矢量艺术、数字绘画、插画创作 github.com/GraphiteEditor/Graphite
Awesome Multi-label Image Recognition Paper List：多标签图像识别文献列表 github.com/JiaweiZhao-git/Awesome-Multi-label-Image-Recognition
Python医学图像处理：无标记CT肺/血管分割 https://theaisummer.com/medical-image-python
MMEditing：图像/视频编辑工具箱 github.com/open-mmlab/mmediting
Crop Map Generation：高分辨率农田地图生成端到端工作流 github.com/nasaharvest/crop-mask
icevision：不可知计算机视觉框架-可插入任意训练库:Fastai，Pytorch-Lightning等 github.com/airctic/icevision
Masterful AI：自动化计算机视觉训练平台 https://www.masterfulai.com/
Satellighte：PyTorch Lightning实现的深度学习卫星图像分类库 github.com/canturan10/satellighte
图像融合(Image Fusion)相关工作/资源整理 github.com/Linfeng-Tang/Image-Fusion
多标签图像识别相关资源大列表 github.com/putao537/Awesome-Multi-label-Image-Recognition
FastDup：大型图片集分析工具，可发现异常、重复和近重复图像、相似性聚类、学习图像间的正常行为和时间交互等 github.com/visualdatabase/fastdup
【Maua：深度学习图像/视频/音频合成库】’Maua - Deep learning toolkit for image, video, and audio synthesis' GitHub: github.com/maua-maua-maua/maua
【Watermark-Removal：图片自动去水印】’Watermark-Removal - a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image' by Zuruoke Okafor GitHub: github.com/zuruoke/watermark-removal
【Rolling-shutter-Effects：图像畸变校正(滚动快门/径向失真/文字失真等)相关文献资源列表】’Rolling-shutter-Effects - A curated list of resources on handling Rolling Shutter effects and Radial Distortions' by Subeesh Vasu GitHub: github.com/subeeshvasu/Awesome-Image-Distortion-Correction
[CV]《DDPM-CD: Remote Sensing Change Detection using Denoising Diffusion Probabilistic Models》W G C Bandara, N G Nair, V M. Patel [Johns Hopkins University] (2022) https://arxiv.org/abs/2206.11892
【P-HAR: 基于深度学习动作识别的色情检测[喵喵]】’P-HAR: Porn Human Action Recognition - deep learning porn classifier' by Rejnald Lleshi GitHub: github.com/rlleshi/phar
【IntraPaint：指导AI图像生成以制作独特创意作品的图形界面】'IntraPaint - An interface for guiding AI image generation to make unique creative works.' by Anthony Brown GitHub: github.com/centuryglass/IntraPaint
[CV]《Face Deblurring using Dual Camera Fusion on Mobile Phones》W Lai, Y Shih, L Chu, X Wu, S Tsai, M Krainin, D Sun, C Liang [Google] (2022) https://arxiv.org/abs/2207.11617
'IMAR Vision Datasets Tools' by Sminchisescu Research Group GitHub: github.com/sminchisescu-research/imar_vision_datasets_tools
【stitching：Python写的图片无缝拼接工具包】’stitching - A Python package for fast and robust Image Stitching' by Lukas Weber GitHub: github.com/lukasalexanderweber/stitching
【哥伦比亚大学《计算机视觉第一原理》课程】《First Principles of Computer Vision》by Shree Nayar Youtube: www.youtube.com/channel/UCf0WB91t8Ky6AuYcQV0CcLw/playlists
[CV]《PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images》C Peng, R Chellappa [Johns Hopkins University] (2022) https://arxiv.org/abs/2208.08049
【CvComposer：OpenCV的高级图形界面，可方便构建工作流、快捷查看结果】’CvComposer - Advanded GUI for OpenCV, to compose various filters and quickly see the result' by Erwan MATHIEU GitHub: github.com/wawanbreton/cvcomposer
【A Toolbox for Video Restoration：视频恢复工具包，包括超分辨率、去模糊、压缩视频质量提升等】’A Toolbox for Video Restoration - Video Restoration Toolbox including FGST (ICML 2022), S2SVR (ICML 2022), etc.' by linjing7 GitHub: github.com/linjing7/VR-Baseline
【NeRF-Factory: PyTorch的NeRF 库】’NeRF-Factory: An awesome PyTorch NeRF library' by Kakao Brain GitHub: github.com/kakaobrain/NeRF-Factory
加速训练 NeRF 模型的项目。英伟达开源的最快只需 5 秒，训练出一只狐狸 NeRF 模型的技术。即根据静态的 2D 图片通过神经网络建模，快速训练出可以放大且从任何角度观察都清晰的图片 https://github.com/NVlabs/instant-ngp
https://github.com/danielgatis/rembg
【实际场景计算机视觉相关文献列表】’CVinW Readings - A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''' by Computer-Vision-in-the-Wild GitHub: github.com/Computer-Vision-in-the-Wild/CVinW_Readings
【光场显著物体检测相关文献资源列表】’Light Field Salient Object Detection: A Review and Benchmark' by kerenfu GitHub: github.com/kerenfu/LFSOD-Survey
[CV]《EVA3D: Compositional 3D Human Generation from 2D Image Collections》F Hong, Z Chen, Y Lan, L Pan, Z Liu [Nanyang Technological University] (2022) https://arxiv.org/abs/2210.04888
【现代图像滤波技术】《A Tour of Modern Image Filtering》by Peyman Milanfar https://users.soe.ucsc.edu/~milanfar/publications/journal/ModernTour.pdf
'数字绘画 - AI绘画资料合集（包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等）' by hua1995116 GitHub: github.com/hua1995116/awesome-ai-painting
【Image-Processing-Node-Editor：用节点编辑器执行图像/视频处理的应用】'Image-Processing-Node-Editor - An application that performs image processing with the node editor' by KazuhitoTakahashi GitHub: github.com/Kazuhito00/Image-Processing-Node-Editor
Microsoft/computervision-recipes: 「Best Practices, code samples, and documentation for Computer Vision.」
https://github.com/microsoft/computervision-recipes
【电子书《计算机视觉：算法与应用(第二版)》】《Computer Vision: Algorithms and Applications, 2nd ed.》by Richard Szeliski, https://szeliski.org/Book/
【MIT《计算机视觉进展》课程】《6.819/6.869: Advances in Computer Vision | MIT CSAIL》 http://6.869.csail.mit.edu/sp22/schedule.html
FLYCV：高性能计算视觉系统(库)】’FLYCV —— High-performance Compute Vision System' by PaddlePaddle GitHub: github.com/PaddlePaddle/FlyCV
【Kangas: 大规模多媒体数据集探索工具，用于探索、分析和可视化大规模多媒体数据】’Kangas: Explore Multimedia Datasets at Scale - a tool for exploring, analyzing, and visualizing large-scale multimedia data' by Comet GitHub: github.com/comet-ml/kangas
[CV]《SinDDM: A Single Image Denoising Diffusion Model》V Kulikov, S Yadin, M Kleiner, T Michaeli [Technion – Israel Institute of Technology] (2022) https://arxiv.org/abs/2211.16582
【计算机视觉性能提升的9个技巧】《9 Computer Vision Tricks to Improve Performance | Kaggle》 https://www.kaggle.com/competitions/happy-whale-and-dolphin/discussion/310105
关于视觉识别领域发展的个人观点 https://zhuanlan.zhihu.com/p/558646681
【Simple OpenCV：在一些移动场景下，替代OpenCV的功能，大部分实现均来自于ncnn】’Simple OpenCV - Make a minimal OpenCV runable on any where, WIP' by JinTian GitHub: github.com/jinfagang/simpleocv
'CV-CUDA™ - an open-source, graphics processing unit (GPU)-accelerated library for cloud-scale image processing and computer vision.' by CVCUDA GitHub: github.com/CvCuda/CV-CUDA
【html_semantic_seg：从DOM创建网页截图语义分割数据集的工具】'html_semantic_seg - Tool to create a dataset of semantic segmentation on website screenshots from their DOM' by David Valdman GitHub: github.com/dmvaldman/html_semantic_seg
【MindCV：基于 MindSpore 开发的，致力于计算机视觉相关技术研发的开源工具箱】'MindCV - A toolbox of vision models and algorithms based on MindSpore' MindSpore Lab GitHub: github.com/mindspore-lab/mindcv
【EveryDream Tools：先进的视觉模型微调工具】'EveryDream Tools - Advanced fine tuning tools for vision models' Victor Hall GitHub: github.com/victorchall/EveryDream
'Implementation of DreamBooth using KerasCV and TensorFlow' Sayak Paul GitHub: github.com/sayakpaul/dreambooth-keras
【不同自动图像增强方法的比较】《Comparing Different Automatic Image Augmentation Methods in PyTorch》by Sebastian Raschka https://sebastianraschka.com/blog/2023/data-augmentation-pytorch.html
'Limbus: Computer Vision pipelining for PyTorch - Open Source async AI pipelines' kornia GitHub: github.com/kornia/limbus
[CV]《Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval》K Saito, K Sohn, X Zhang, C Li, C Lee, K Saenko, T Pfister [Google Research & Google Cloud AI Research & Boston University] (2023) https://arxiv.org/abs/2302.03084
【rerun：Rust写的计算机视觉可视化框架】’rerun - Log images, point clouds, etc, and visualize them effortlessly. Built in Rust using egui' rerun.io GitHub: github.com/rerun-io/rerun
【AdverseCleaner：基于各向异性过滤的高效图片对抗噪声消除工具，CPU即可运行】’AdverseCleaner - Remove adversarial noise from images' Lvmin Zhang GitHub: github.com/lllyasviel/AdverseCleaner
【CleanVision：用于自动发现图像数据集中问题的工具，目前可以检测原始图像本身的问题，例如模糊、黑暗、过曝、重复、缺失等，并可用于任何机器学习任务(分类、分割、目标检测、姿态估计、关键点检测等)】’CleanVision - Automatically find issues in image datasets and practice data-centric computer vision' Cleanlab GitHub: github.com/cleanlab/cleanvision
ReBotNet是一种高效的视频增强框架，可以实时增强视频通话和视频流等实际应用场景下的视频质量，而比现有方法更省时、更省计算和内存。 https://arxiv.org/abs/2303.13504
MULLER是一种轻量的、基于多层拉普拉斯分解的图像缩放方法，能有效提高图像识别模型的性能和推理效率。 https://arxiv.org/abs/2304.02859 [CV]《MULLER: Multilayer Laplacian Resizer for Vision》Z Tu, P Milanfar, H Talebi [Google Research] (2023)
palette.fm 一个用AI给老照片上色的网站。和其他配色网站不同的是你可以提供配色方面的关键词，然后系统会根据你给定的关键词来配色。 500*500分辨率下免费。
推荐一款 AI 图像无损放大神器：Upscayl，可以快速将模糊图片秒变高清图。我用了挺长一段时间了，效果很不错。 支持 macOS、Windows、Linux 等主流操作系统，底层模型用的是腾讯之前开源的 Real-ESRGAN，看了下官方的对比测试，效果要比 Waifu2x 的好不少。 GitHub：github.com/upscayl/upscayl
【Trainbot：一个计算机视觉项目，用Go编写，能监视火车轨道，检测火车，并拼接它们的图像，适用于任何video4linux USB摄像头或Raspberry Pi相机v3模块】'Trainbot - Trainbot watches a piece of train track, detects trains, and stitches together images of them. Computer vision exercise in Go.' Jo M GitHub: github.com/jo-m/trainbot
实用的图像/视频修复算法 🔗github.com/xinntao/Real-ESRGAN
一个开源的命令行工具：Background Remover，可借助 AI 能力，快速移除图像和视频背景。 Background Remover：github.com/nadermx/backgroundremover 项目底层技术用的是 u2net，一个开源的目标检测算法。 u2net：github.com/xuebinqin/U-2-Net
《Photoswap: Personalized Subject Swapping in Images | Photoswap: 图像中的个性化主题替换》 Photoswap，只需要一个参考图像而对参考图像进行预训练，就可以对目标图像进行无缝局部替换同时保留图像原始风格和构图。 项目首页：photoswap.github.io
pixian.ai，能够利用 AI 一键移除各种图像背景，并支持在线调整图片分辨率、背景颜色等等。 目前在 Web 端可免费使用，效果不错。抠出来的图结合 AI 绘画和图像编辑工具，可以做出不少有意思的场景。
【PyFeats：一款开源软件，用于提取图像特征。支持多种特征提取方法，如纹理特征、形态学特征、直方图特征、多尺度特征等】'PyFeats - Open source software for image feature extraction.' Nikolaos Giakoumoglou GitHub: github.com/giakou4/pyfeats
提出一种强大的图像标签基础模型——Recognize Anything Model(RAM)，通过自动文本语义解析获得大规模无标注图像标签，然后通过统一的标题和标签任务训练一个初步的模型，接着使用数据引擎生成额外的标注并清理错误标注，最后使用处理过的数据重新训练模型并使用较小但更高质量的数据集进行微调。 https://arxiv.org/abs/2306.03514 [CV]《Recognize Anything: A Strong Image Tagging Model》Y Zhang, X Huang, J Ma, Z Li, Z Luo, Y Xie, Y Qin, T Luo, Y Li, S Liu, Y Guo, L Zhang [OPPO Research Institute] (2023)
【Palette.fm：最先进的照片自动上色服务】《Colorize Photos - Try Free without Sign-up - Palette.fm》 https://palette.fm/
'clip.cpp - CLIP inference in plain C/C++ with no extra dependencies' M. Yusuf Sarıgöz GitHub: github.com/monatis/clip.cpp
background-removal-js：完全在浏览器中工作的去图片背景工具 地址：github.com/imgly/background-removal-js
DragGAN图像编辑神器，源代码已经公开。 地址：github.com/XingangPan/DragGAN
【Semaphore Games：全身游戏控制器，使用OpenCV和MediaPipe的姿态检测实时捕捉身体动作并转化为键盘命令。在大空间、良好光照和纯色背景下体验最佳。通过伸臂、抬腿等动作来输入自定义按键或按键组合】'Semaphore Games - Full-body game controller built with Python, OpenCV, Mediapipe' everythingishacked GitHub: github.com/everythingishacked/Gamebody
【图像匹配、姿态估计相关论文列表】’Image-Matching-Paper-List - A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.' Xi Li GitHub: github.com/chicleee/Image-Matching-Paper-List
【LVM-Med：用于医学图像的自监督学习大规模视觉预训练模型，可用于2D-3D分割、图像分类和目标检测等下游任务】'LMV-Med pre-trained models' duynhm GitHub: github.com/duyhominhnguyen/LVM-Med
【LEDITS图像语义编辑Demo】《LEDITS - a Hugging Face Space by editing-images》 https://huggingface.co/spaces/editing-images/ledits
提出SAM-PT，一种将稀疏点跟踪结合SAM进行视频分割的方法，能有效地处理动态视频中的跟踪和分割问题，并且在各种视频对象分割基准测试中都显示出了强大的零样本性能。 https://arxiv.org/abs/2307.01197 [CV]《Segment Anything Meets Point Tracking》F Rajič, L Ke, Y Tai, C Tang, M Danelljan, F Yu [ETH Zurich & HKUST] (2023)