SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Computer Vision Open-Source Projects
-
Note that the 'Jump Flood Algorithm' is O(N log N) where N is the number of pixels. There is a better O(N) algorithm which can be parallelized over the number of rows/columns of an image:
https://news.ycombinator.com/item?id=36809404
Unfortunately, it requires random access writes (compute shaders) if you want to run it on the GPU. But if CPU is fine, here are a few implementations:
JavaScript: https://parmanoir.com/distance/
C: https://github.com/983/df
C++: https://github.com/opencv/opencv/blob/4.x/modules/imgproc/sr...
Python: https://github.com/pymatting/pymatting/blob/afd2dec073cb08b8...
-
CodeRabbit
CodeRabbit: AI Code Reviews for Developers. Revolutionize your code reviews with AI. CodeRabbit offers PR summaries, code walkthroughs, 1-click suggestions, and AST-based analysis. Boost productivity and code quality across all major languages with each PR.
-
-
Syncthing, python face_recognition [1], a static gallery (sigal [2]), and a few lines of bash and its fully automatic. I can even share links with family.
[1] https://github.com/ageitgey/face_recognition
[2] https://github.com/saimn/sigal
-
Project mention: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos | news.ycombinator.com | 2025-01-25
They did it on their own computer. https://github.com/ultralytics/ultralytics
-
Project mention: The Top 9️⃣ Repositories to learn Python programming + Resources (Extra) 🤯 | dev.to | 2024-11-06
⭐️ AI For Beginners on GitHub.
-
openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
-
Project mention: Integrating MediaPipe with DeepSeek for Enhanced AI Performance | dev.to | 2025-02-03
Code Examples: Check out the MediaPipe and LLM Integration Examples provided by Google AI Edge.
-
Nutrient
Nutrient – The #1 PDF SDK Library, trusted by 10K+ developers. Other PDF SDKs promise a lot - then break. Laggy scrolling, poor mobile UX, tons of bugs, and lack of support cost you endless frustrations. Nutrient’s SDK handles billion-page workloads - so you don’t have to debug PDFs. Used by ~1 billion end users in more than 150 different countries.
-
applied-ml
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
-
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Project mention: Ask HN: What is the best method for turning a scanned book as a PDF into text? | news.ycombinator.com | 2025-02-16I have tried a bunch of things. This is what worked best for me: Surya [0]. It can run fully local on your laptop. I also tried EasyOCR [1], which is also quite good. I haven't tried this myself, but I will look at Paddle [2] if the previous two don't float your boat.
All of these are OSS, and you don't need to pay a dime to anyone.
[0]: https://github.com/VikParuchuri/surya
[1]: https://github.com/JaidedAI/EasyOCR
[2]: https://github.com/PaddlePaddle/Paddle
-
d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
-
-
-
500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code
500 AI Machine learning Deep learning Computer vision NLP Projects with code
500 AI machine learning NLP programming projects
-
darknet
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet ) (by AlexeyAB)
-
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
-
-
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
If instead you have a cohort on hand — -i.e., you do not want to send your data to a third party for any reason, or perhaps you have energetic undergrads — -then you could alternatively consider local, open-source annotation such as CVAT and Label Studio. Finally, nowadays, you might instead work with Large Multimodal Models to have them annotate your data; more on this awkward angle later.
-
datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Project mention: 20 Open Source Tools I Recommend to Build, Share, and Run AI Projects | dev.to | 2024-11-13Datasets library repository for accessing and sharing datasets with the community.
-
-
AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
-
"test"(100,000 images) isn't supported so I requested the feature on GitHub.
-
Project mention: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation | news.ycombinator.com | 2025-01-21
-
gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Project mention: Show HN: Show HN: SplatGallery – A Community-Driven Gallery for Gaussian Splats | news.ycombinator.com | 2024-11-04 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
Computer Vision discussion
Computer Vision related posts
-
Integrating MediaPipe with DeepSeek for Enhanced AI Performance
-
Voxel51 Filtered Views Newsletter - January 17, 2025
-
How to Make the Best Self-Driving Dataset
-
Developing an ASL App with Kaggle’s Top Model and Customized MediaPipe Gesture Model
-
How to draw an outline in a video game
-
Show HN: Control your Roku with only your hand gestures
-
Convert LabelMe Annotations to YOLO Format with labelme-to-yolo
-
A note from our sponsor - SaaSHub
www.saashub.com | 18 Feb 2025
Index
What are some of the best open-source Computer Vision projects? This list will help you:
# | Project | Stars |
---|---|---|
1 | OpenCV | 80,548 |
2 | cs-video-courses | 68,109 |
3 | Face Recognition | 54,105 |
4 | ultralytics | 36,380 |
5 | AI-For-Beginners | 36,005 |
6 | openpose | 31,837 |
7 | mediapipe | 28,580 |
8 | applied-ml | 27,690 |
9 | EasyOCR | 25,546 |
10 | d2l-en | 24,927 |
11 | supervision | 24,868 |
12 | pytorch-CycleGAN-and-pix2pix | 23,522 |
13 | 500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code | 22,094 |
14 | darknet | 21,901 |
15 | vit-pytorch | 21,725 |
16 | learnopencv | 21,597 |
17 | label-studio | 20,684 |
18 | datasets | 19,619 |
19 | CVPR2024-Papers-with-Code | 18,780 |
20 | AirSim | 16,783 |
21 | vision | 16,544 |
22 | instant-ngp | 16,286 |
23 | gaussian-splatting | 15,755 |