Computer Vision
Detection, segmentation, OCR, and vision pipelines — production CV open source.
384 projects
See methodology for ranking rules; order uses public GitHub metrics within this scenario.
| Rank | Project | Stars | Forks | Updated | License |
|---|---|---|---|---|---|
| 221 |
eos
A lightweight 3D Morphable Face Model library in modern C++ |
2.0K | 594 | 05/01/25 | Apache-2.0 |
| 222 |
3DObjectTracking
Algorithms and Publications on 3D Object Tracking |
1.0K | 182 | 08/25/25 | MIT |
| 223 |
Augmentor
Image augmentation library in Python for machine learning. |
5.1K | 870 | 03/21/24 | MIT |
| 224 |
UniRepLKNet
[CVPR 2024 & TPAMI 2025] UniRepLKNet |
1.1K | 63 | 08/10/25 | Apache-2.0 |
| 225 |
KAIR
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR |
3.5K | 705 | 10/02/24 | MIT |
| 226 |
XScene-UEPlugin
A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model. |
1.1K | 125 | 07/30/25 | Apache-2.0 |
| 227 |
fast-reid
SOTA Re-identification Methods and Toolbox |
4.0K | 879 | 07/30/24 | Apache-2.0 |
| 228 |
PythonSIFT
A clean and concise Python implementation of SIFT (Scale-Invariant Feature Transform) |
1.0K | 261 | 08/13/25 | MIT |
| 229 |
PerceptualSimilarity
LPIPS metric. pip install lpips |
4.3K | 523 | 07/02/24 | BSD-2-Clause |
| 230 |
ComfyUI-WD14-Tagger
A ComfyUI extension allowing for the interrogation of booru tags from images. |
1.2K | 123 | 07/11/25 | MIT |
| 231 |
darkflow
Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices |
6.1K | 2.0K | 10/23/23 | GPL-3.0 |
| 232 |
cv
Rust CV mono-repo. Contains pure-Rust dependencies which attempt to encapsulate the capability of OpenCV, OpenMVG, and vSLAM frameworks in a cohesive set of APIs. |
1.1K | 70 | 07/22/25 | Other |
| 233 |
VisoMaster
Powerful & Easy-to-Use Video Face Swapping and Editing Software |
2.1K | 358 | 03/11/25 | GPL-3.0 |
| 234 |
MixTeX-Latex-OCR
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows. |
1.6K | 97 | 04/24/25 | AGPL-3.0 |
| 235 |
neuralangelo
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023) |
4.6K | 404 | 04/14/24 | Other |
| 236 |
simplerecon
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions |
1.4K | 130 | 05/09/25 | Other |
| 237 |
GPUImage2
GPUImage 2 is a BSD-licensed Swift framework for GPU-accelerated video and image processing. |
4.9K | 618 | 02/16/24 | BSD-3-Clause |
| 238 |
mmyolo
OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc. |
3.5K | 631 | 07/14/24 | GPL-3.0 |
| 239 |
pytracking
Visual tracking library based on PyTorch. |
3.5K | 614 | 08/08/24 | GPL-3.0 |
| 240 |
UniDepth
Universal Monocular Metric Depth Estimation |
1.2K | 118 | 05/18/25 | Other |