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.

81–100 of 384

Rank Project Stars Forks
81 sparrow

Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM

5.2K 519
82 openMVG

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

6.5K 1.7K
83 watermark-removal

a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image

5.1K 599
84 trace.moe

Timestamp Retrieval for Anime Clips Everywhere

5.0K 263
85 nsfw_data_scraper

Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier

12.6K 2.8K
86 torchgeo

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

4.2K 581
87 Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

6.0K 552
88 AliceVision

3D Computer Vision Framework

3.5K 878
89 obs-backgroundremoval

An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.

4.5K 288
90 scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

3.8K 479
91 lightly

A python library for self-supervised learning on images.

3.8K 356
92 segment-geospatial

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

4.1K 440
93 super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

5.1K 592
94 modlens

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).

3.8K 110
95 vision-agent

This tool has been deprecated. Use Agentic Document Extraction instead.

5.3K 601
96 co-tracker

CoTracker is a model for tracking any point (pixel) on a video.

5.1K 386
97 U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

9.9K 1.6K
98 nunif

Misc; latest version of waifu2x; 2D video to stereo 3D video conversion

3.4K 282
99 geoai

GeoAI: Artificial Intelligence for Geospatial Data

3.3K 472
100 vjepa2

PyTorch code and models for VJEPA2 self-supervised learning from video.

4.5K 559