Open-source computer-vision software
2359 open-source libraries, tools and applications tagged computer-vision, ranked by how closely computer-vision is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
2359 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| TorchCV TorchCV is a PyTorch-based framework providing reimplementations of deep learning models for major computer vision tasks. It covers image c… | 32 | 2252 | maintenance |
| hustvl/YOLOP YOLOP is a multi-task deep learning network that jointly performs traffic object detection, drivable area segmentation, and lane detection … | 32 | 2249 | maintenance |
| idealo/image-quality-assessment A Python implementation of Google's NIMA (Neural Image Assessment) models that predict the aesthetic and technical quality of images using … | 10 | 2241 | maintenance |
| Daniil-Osokin/lightweight-human-pose-estimation.pytorch A PyTorch implementation of Lightweight OpenPose for real-time 2D multi-person human pose estimation on CPU. It detects up to 18 body keypo… | 32 | 2237 | maintenance |
| Jongchan/attention-module Official PyTorch implementation of two attention modules for convolutional neural networks: BAM (Bottleneck Attention Module) and CBAM (Con… | 32 | 2237 | maintenance |
| KaiyangZhou/CoOp A research codebase implementing prompt learning methods (CoOp and CoCoOp) for adapting vision-language models like CLIP to downstream clas… | 32 | 2236 | maintenance |
| machrisaa/tensorflow-vgg A Python library implementing the VGG16 and VGG19 convolutional neural networks in TensorFlow, loading pretrained weights from npy files fo… | 32 | 2235 | maintenance |
| uzh-rpg/rpg_svo SVO is a semi-direct monocular visual odometry pipeline written in C++ that estimates camera motion from image sequences. It is research co… | 32 | 2233 | maintenance |
| mit-han-lab/temporal-shift-module PyTorch implementation of the Temporal Shift Module (TSM), an ICCV 2019 technique that adds temporal modeling to 2D CNNs at zero extra comp… | 32 | 2223 | maintenance |
| gligen/GLIGEN GLIGEN is a research library for open-set grounded text-to-image generation, extending frozen diffusion models with spatial grounding via b… | 32 | 2222 | maintenance |
| ZQCNN ZQCNN is a lightweight deep learning inference framework written in C/C++ that runs on Windows, Linux, and ARM-Linux. It ships with demos f… | 57 | 2212 | maintenance |
| ashawkey/torch-ngp A PyTorch implementation of instant-ngp's NeRF and SDF components with CUDA extensions and an interactive GUI for training and visualizatio… | 32 | 2210 | maintenance |
| google-research/uda Google Research's reference implementation of Unsupervised Data Augmentation (UDA), a semi-supervised learning method that uses advanced da… | 10 | 2205 | maintenance |
| yhenon/pytorch-retinanet A PyTorch implementation of the RetinaNet object detection model with focal loss, designed for readability and easy modification. It includ… | 10 | 2204 | maintenance |
| magicleap/SuperPointPretrainedNetwork A PyTorch pre-trained implementation of the SuperPoint fully convolutional neural network for real-time interest point detection and descri… | 32 | 2196 | maintenance |
| tianweiy/CenterPoint Official PyTorch implementation of CenterPoint, a CVPR 2021 method that performs 3D object detection and tracking from LiDAR point clouds b… | 23 | 2195 | maintenance |
| githubharald/SimpleHTR A Handwritten Text Recognition (HTR) system implemented in TensorFlow that recognizes text from images of single words or text lines, train… | 69 | 2191 | maintenance |
| vchoutas/smplify-x SMPLify-X is the official PyTorch implementation of the CVPR 2019 paper 'Expressive Body Capture: 3D Hands, Face, and Body from a Single Im… | 32 | 2174 | maintenance |
| open-mmlab/mmrotate MMRotate is an open-source PyTorch toolbox for rotated object detection, part of the OpenMMLab project. It provides modular components, mul… | 23 | 2168 | maintenance |
| bubbliiiing/yolov4-pytorch A PyTorch implementation of the YOLOv4 object detection model with full training, prediction, and evaluation scripts. It supports training … | 23 | 2163 | maintenance |
| facebookresearch/pycls pycls is a PyTorch-based codebase for image classification research developed by Facebook AI Research. It provides implementations of stand… | 10 | 2161 | maintenance |
| kingyiusuen/image-to-latex A PyTorch application that converts images of LaTeX math equations into LaTeX code using a ResNet-18 encoder and Transformer decoder traine… | 32 | 2160 | maintenance |
| jeonsworld/ViT-pytorch A PyTorch reimplementation of Google's Vision Transformer (ViT) for image classification, based on the paper 'An Image is Worth 16x16 Words… | 32 | 2159 | maintenance |
| ankush-me/SynthText SynthText is a Python tool for generating synthetic scene-text images with ground-truth bounding boxes, as described in the CVPR 2016 paper… | 32 | 2146 | maintenance |
| satoshiiizuka/siggraph2016_colorization A Torch7 implementation of the SIGGRAPH 2016 paper 'Let there be Color!' that automatically colorizes grayscale images using a deep network… | 32 | 2142 | maintenance |
| Kimera Kimera is a modular C++ library for real-time metric-semantic SLAM that builds semantically annotated 3D meshes from camera and inertial da… | 32 | 2130 | maintenance |
| Anime2Sketch Anime2Sketch is a PyTorch-based sketch extractor that converts anime art, illustrations, and manga into line drawings using pretrained GAN … | 74 | 2128 | maintenance |
| chuanqi305/MobileNet-SSD A Caffe implementation of the MobileNet-SSD object detection network with pretrained weights on the VOC0712 dataset achieving mAP of 0.727.… | 43 | 2126 | maintenance |
| AIZOO FaceMaskDetection An open-source face mask detection project providing a lightweight SSD-based model (1.01M parameters) with inference code for PyTorch, Tens… | 32 | 2122 | maintenance |
| bubbliiiing/yolo3-pytorch A PyTorch implementation of the YOLOv3 object detection model with full training, prediction, and evaluation scripts. It supports training … | 23 | 2111 | maintenance |
| graphific/DeepDreamVideo A Python-based command-line tool that applies Google's DeepDream algorithm to videos by extracting frames, running a pretrained deep neural… | 32 | 2107 | maintenance |
| doyubkim/fluid-engine-dev Jet is a C++11 fluid simulation engine SDK for computer graphics, created alongside the book 'Fluid Engine Development'. It provides SPH, P… | 23 | 2102 | maintenance |
| bgshih/crnn An implementation of the Convolutional Recurrent Neural Network (CRNN), combining CNN, RNN, and CTC loss for image-based sequence recogniti… | 32 | 2101 | maintenance |
| dog-qiuqiu/Yolo-Fastest Yolo-Fastest is an ultra-lightweight YOLO-based object detection algorithm and model zoo, with only ~250 MFLOPs and a 666KB ncnn model. It … | 23 | 2101 | maintenance |
| qubvel/efficientnet A Keras and TensorFlow Keras reimplementation of the EfficientNet convolutional neural network family (B0-B7), including ImageNet-pretraine… | 23 | 2098 | maintenance |
| facebookresearch/swav PyTorch implementation of SwAV, a self-supervised method for pre-training convolutional networks without labels by swapping cluster assignm… | 10 | 2093 | maintenance |
| RootKit-Org/AI-Aimbot A Python application that uses a YOLOv5-based computer vision model to detect humanoid targets on screen and assist aiming in FPS games lik… | 10 | 2075 | maintenance |
| ppwwyyxx/OpenPano OpenPano is a C++ panorama stitching program written from scratch without vision libraries, implementing the Automatic Panoramic Image Stit… | 23 | 2074 | maintenance |
| UniversalDataTool/universal-data-tool Universal Data Tool is a web and desktop application for collaboratively annotating images, text, audio, and documents, supporting tasks li… | 24 | 2073 | maintenance |
| ozan-oktay/Attention-Gated-Networks A PyTorch implementation of attention gates for convolutional neural networks, applied to U-Net and VGG-16 architectures. It targets medica… | 32 | 2065 | maintenance |
| knightcrawler25/GLSL-PathTracer A toy physically based GPU path tracer written in C++ that runs its rendering loop in GLSL fragment shaders via OpenGL. It supports feature… | 23 | 2064 | maintenance |
| Ultra-Fast-Lane-Detection A PyTorch implementation of the ECCV 2020 paper 'Ultra Fast Structure-aware Deep Lane Detection', providing training and evaluation code fo… | 32 | 2061 | maintenance |
| strawlab/python-pcl Python bindings for the Point Cloud Library (PCL), implemented with Cython. It exposes PCL's 3D point cloud processing algorithms (filterin… | 10 | 2054 | maintenance |
| danmacnish/cartoonify A Python application that converts photographs into hand-drawn-style cartoons using a neural network for object recognition combined with t… | 32 | 2051 | maintenance |
| PyMesh/PyMesh PyMesh is a rapid prototyping geometry processing library for Python, with performance-critical algorithms implemented in C++ and exposed v… | 23 | 2050 | maintenance |
| PyTorch-Encoding A PyTorch computer vision toolkit with optimized CUDA backend, providing encoding layers, synchronized multi-GPU batch normalization, and p… | 65 | 2045 | maintenance |
| apple/ml-fastvit Official PyTorch implementation of FastViT, a fast hybrid vision transformer architecture using structural reparameterization, published at… | 71 | 2039 | maintenance |
| AnimeGAN AnimeGAN is a family of TensorFlow-based generative adversarial network models (v1, v2, v3) that convert landscape photos and videos into a… | 36 | 2036 | maintenance |
| jiupinjia/SkyAR SkyAR is the official PyTorch implementation of the paper 'Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos'. It perf… | 32 | 2029 | maintenance |
| Talking Head Anime from a Single Image Demo applications for the 'Talking Head Anime from a Single Image' research project, built with PyTorch. It includes a manual poser for ani… | 32 | 2028 | maintenance |
| darglein/ADOP ADOP is a point-based differentiable neural rendering pipeline for scene refinement and novel view synthesis, implemented in C++/CUDA with … | 23 | 2028 | maintenance |
| mingyuliutw/UNIT UNIT is NVIDIA's research implementation of unsupervised image-to-image translation networks (NIPS 2017), translating images across domains… | 32 | 2026 | maintenance |
| WongKinYiu/ScaledYOLOv4 PyTorch implementation of Scaled-YOLOv4, which scales the Cross Stage Partial Network (CSP) across model sizes from tiny to P7 for object d… | 23 | 2024 | maintenance |
| lucasb-eyer/pydensecrf PyDenseCRF is a Cython-based Python wrapper around Philipp Krähenbühl's fully-connected (dense) conditional random field implementation wit… | 32 | 2022 | maintenance |
| hila-chefer/Transformer-Explainability Official PyTorch implementation of the CVPR 2021 paper 'Transformer Interpretability Beyond Attention Visualization', providing relevance-b… | 32 | 2019 | maintenance |
| tinghuiz/SfMLearner SfMLearner is a TensorFlow implementation of the CVPR 2017 paper 'Unsupervised Learning of Depth and Ego-Motion from Video'. It trains mode… | 32 | 2016 | maintenance |
| facebookresearch/Detic Detic is the official code release for the ECCV 2022 paper 'Detecting Twenty-thousand Classes using Image-level Supervision'. It is an open… | 32 | 2013 | maintenance |
| Zz-ww/SadTalker-Video-Lip-Sync A Python tool built on SadTalker that generates lip-synced video from an audio file and a source video, with configurable face/lip region e… | 30 | 2012 | maintenance |
| open-mmlab/mmgeneration MMGeneration is a PyTorch-based toolkit from OpenMMLab for training and applying generative models, with a focus on GANs and support for di… | 23 | 2011 | maintenance |
| minimaxir/person-blocker A Python command-line script that automatically censors ('blocks') people and up to 80 other object types in images using a pretrained Mask… | 32 | 2009 | maintenance |
| WongKinYiu/yolor PyTorch implementation of the YOLOR paper 'You Only Learn One Representation: Unified Network for Multiple Tasks', a real-time object detec… | 23 | 2006 | maintenance |
| JDAI-CV/FaceX-Zoo FaceX-Zoo is a PyTorch toolbox for face recognition that provides training modules with various state-of-the-art supervisory heads and back… | 32 | 2000 | maintenance |
| vsitzmann/siren Official PyTorch implementation of SIREN, a neural network architecture using periodic (sine) activation functions for implicit neural repr… | 32 | 2000 | maintenance |
| haitongli/knowledge-distillation-pytorch A PyTorch framework for running knowledge distillation experiments, supporting both shallow (teacher-to-small-CNN) and deep distillation on… | 32 | 1999 | maintenance |
| apple/ml-cvnets CVNets is Apple's open-source PyTorch library for training computer vision networks, covering classification, detection, segmentation, vide… | 75 | 1993 | maintenance |
| HobbitLong/PyContrast PyContrast is a PyTorch library providing reference implementations of contrastive learning methods such as InstDis, CMC, and MoCo, along w… | 32 | 1992 | maintenance |
| albertpumarola/GANimation Official PyTorch implementation of GANimation, an ECCV'18 research paper that animates facial expressions in a single image using a GAN con… | 32 | 1989 | maintenance |
| guanshuicheng/invoice A Flask-based OCR microservice that recognizes Chinese VAT invoices (electronic, regular, and special) using a YOLOv3 + CRNN + CTC deep lea… | 32 | 1979 | maintenance |
| WuJie1010/Facial-Expression-Recognition.Pytorch A PyTorch implementation of CNN-based facial expression recognition achieving state-of-the-art accuracy on FER2013 (73.112%) and CK+ (94.64… | 32 | 1979 | maintenance |
| KumarRobotics/msckf_vio A stereo visual-inertial odometry package implementing the Multi-State Constraint Kalman Filter (MSCKF) in C++ on ROS. It fuses synchronize… | 32 | 1979 | maintenance |
| Tencent/ObjectDetection-OneStageDet OneStageDet (OSD) is a PyTorch-based single-stage object detection framework from Tencent implementing YOLOv2 and YOLOv3 with plans to unif… | 42 | 1976 | maintenance |
| Hitachi-Automotive-And-Industry-Lab/semantic-segmentation-editor A web-based labeling tool for creating AI training datasets from bitmap images (.jpg/.png) and point clouds (.pcd). Built as a Meteor app w… | 23 | 1976 | maintenance |
| google/nerfies Nerfies is the official JAX implementation of Deformable Neural Radiance Fields, which reconstructs non-rigidly deforming scenes from casua… | 10 | 1974 | maintenance |
| FoundationVision/LlamaGen LlamaGen is a family of autoregressive image generation models that apply next-token prediction, as in Llama-style LLMs, to visual generati… | 25 | 1970 | maintenance |
| yehengchen/Object-Detection-and-Tracking A collection of Python implementations combining YOLO-based object detection with SORT and DeepSORT multi-object tracking. It includes exam… | 32 | 1965 | maintenance |
| jesolem/PCV PCV is a pure Python computer vision library containing the code from the book 'Programming Computer Vision with Python' by Jan Erik Solem.… | 32 | 1960 | maintenance |
| HuTianQi/SmartOpenCV SmartOpenCV is an enhancement library for OpenCV on Android that fixes numerous image preview issues in the official OpenCV Android SDK, su… | 23 | 1960 | maintenance |
| mit-han-lab/once-for-all Once-for-All (OFA) is a PyTorch library implementing the ICLR 2020 Once-for-All network, which trains a single supernet that can be special… | 23 | 1953 | maintenance |
| hukaixuan19970627/yolov5_obb A PyTorch implementation of YOLOv5 extended for oriented (rotated) object detection using Circular Smooth Label (CSL) angle encoding. It pr… | 32 | 1949 | maintenance |
| peng-zhihui/DeepVision DeepVision is an Android-based computer vision algorithm inference and validation framework by peng-zhihui. It decouples data flow control,… | 32 | 1941 | maintenance |
| PandaOCR PandaOCR is a free Windows desktop OCR tool that captures screen regions and recognizes text using many cloud OCR engines (Sogou, Tencent, … | 71 | 1929 | maintenance |
| s9xie/hed Reference implementation of Holistically-Nested Edge Detection (HED), a deep learning edge and boundary detection model built on a modified… | 23 | 1928 | maintenance |
| mp3guy/ElasticFusion ElasticFusion is a real-time dense visual SLAM system that builds globally consistent surfel-based 3D maps of room-scale environments from … | 44 | 1927 | maintenance |
| WongKinYiu/PyTorch_YOLOv4 A PyTorch implementation of the YOLOv4 real-time object detection model, based on ultralytics/yolov3. It includes research extensions such … | 23 | 1907 | maintenance |
| Pyramid Vision Transformer Official PyTorch implementation of the Pyramid Vision Transformer (PVTv1 and PVTv2) model series, providing pretrained backbone networks fo… | 23 | 1905 | maintenance |
| astorfi/lip-reading-deeplearning A TensorFlow implementation of coupled 3D convolutional neural networks for cross audio-visual matching recognition, accompanying an IEEE A… | 23 | 1902 | maintenance |
| ronghuaiyang/arcface-pytorch A PyTorch implementation of ArcFace, a deep metric learning approach for face recognition that adds angular margin penalties to face embedd… | 32 | 1901 | maintenance |
| junshutang/Make-It-3D Make-It-3D is a research codebase from an ICCV 2023 paper that creates high-fidelity 3D content from a single image using a 2D diffusion mo… | 31 | 1898 | maintenance |
| NVIDIA-AI-IOT/deepstream_python_apps Python bindings and sample applications for NVIDIA's DeepStream SDK, built with Pybind11 and Gst Python for constructing video analytics pi… | 53 | 1893 | maintenance |
| zjhuang22/maskscoring_rcnn Official PyTorch implementation of Mask Scoring R-CNN (CVPR 2019), built on maskrcnn-benchmark. It adds a network block that learns the qua… | 32 | 1893 | maintenance |
| TreB1eN/InsightFace_Pytorch A PyTorch reimplementation of InsightFace/ArcFace for face recognition, including backbone models (IR-SE50, MobileFacenet) and pretrained w… | 32 | 1893 | maintenance |
| Ucas-HaoranWei/Vary Official ECCV 2024 implementation of Vary, a method for scaling up the vision vocabulary of large vision-language models. It provides train… | 27 | 1890 | maintenance |
| Duankaiwen/CenterNet Official PyTorch implementation of CenterNet, a one-stage keypoint-triplet-based object detector built on CornerNet. It trains from scratch… | 32 | 1886 | maintenance |
| zhoubolei/CAM Reference implementation of Class Activation Mapping (CAM), a CVPR'16 technique that visualizes which image regions a CNN attends to when p… | 32 | 1884 | maintenance |
| TixiaoShan/LVI-SAM LVI-SAM is a tightly-coupled Lidar-Visual-Inertial Odometry and mapping system implemented in C++ on ROS, combining LIO-SAM and VINS-Mono a… | 32 | 1884 | maintenance |
| mpatacchiola/deepgaze Deepgaze is a Python computer vision library for human-computer interaction built on OpenCV and TensorFlow. It provides CNN-based head pose… | 32 | 1882 | maintenance |
| open-mmlab/mmaction MMAction is an open-source PyTorch toolbox for video action understanding, covering action recognition, temporal action detection, and spat… | 32 | 1875 | maintenance |
| Sierkinhane/CRNN_Chinese_Characters_Rec A PyTorch implementation of a CRNN (convolutional recurrent neural network) model for recognizing Chinese characters in images. It includes… | 32 | 1871 | maintenance |
| SSD Keras Implementation A Keras implementation of the Single Shot MultiBox Detector (SSD) object detection architecture, with ports of the original trained weights… | 23 | 1868 | maintenance |
| xiaolai-sqlai/mobilenetv3 A PyTorch implementation of the MobileNetV3 architecture with retrained pre-trained weights that outperform the original paper and torchvis… | 32 | 1865 | maintenance |