InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now. Learn more →
Top 23 Python Segmentation Projects
-
segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
-
Civic Auth
Simple auth for Python backends. Drop Civic Auth into your Python backend with just a few lines of code. Email login, SSO, and route protection built-in. Minimal config. Works with FastAPI, Flask, or Django.
-
boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models
-
-
-
Pointnet_Pointnet2_pytorch
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
-
-
Sevalla
Deploy and host your apps and databases, now with $50 credit! Sevalla is the PaaS you have been looking for! Advanced deployment pipelines, usage-based pricing, preview apps, templates, human support by developers, and much more!
-
segment-geospatial
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
-
HRNet-Semantic-Segmentation
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
-
-
-
-
detrex
detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.
-
comic-translate
Desktop app for automatically translating comics - BDs, Manga, Manhwa, Fumetti and more in a variety of formats (Image, Pdf, Epub, cbr, cbz, etc) and in multiple languages.
Project mention: Show HN: Instantly Translate Manga – TranslateManga | news.ycombinator.com | 2025-02-26In addition to lots of commercial competition, there's also a halfway decent open source comic translation app that uses automatic OCR + LLMs (byok).
https://github.com/ogkalu2/comic-translate
-
-
-
-
-
-
-
image-background-remove-tool
✂️ Automated high-quality background removal framework for an image using neural networks. ✂️
-
medicaldetectiontoolkit
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
-
sd-webui-inpaint-anything
Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.
-
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
Python Segmentation discussion
Python Segmentation related posts
-
Instance segmentation of small objects in grainy drone imagery
-
12-Jun-2023
-
Segment Anything in High Quality
-
Segment Anything in High Quality
-
GitHub - SysCV/sam-hq: Segment Anything in High Quality
-
Anyone using segment-geospatial?
-
Where to even begin to extract yellow spots from these pictures?
-
A note from our sponsor - InfluxDB
www.influxdata.com | 31 Aug 2025
Index
What are some of the best open-source Segmentation projects in Python? This list will help you:
# | Project | Stars |
---|---|---|
1 | segmentation_models.pytorch | 10,834 |
2 | boxmot | 7,631 |
3 | nnUNet | 7,166 |
4 | pointnet | 5,184 |
5 | segmentation_models | 4,877 |
6 | Pointnet_Pointnet2_pytorch | 4,306 |
7 | pointnet2 | 3,454 |
8 | segment-geospatial | 3,391 |
9 | HRNet-Semantic-Segmentation | 3,263 |
10 | BlenderProc | 3,191 |
11 | UNetPlusPlus | 2,494 |
12 | LISA | 2,380 |
13 | detrex | 2,198 |
14 | comic-translate | 1,963 |
15 | ml-cvnets | 1,902 |
16 | XMem | 1,886 |
17 | cellpose | 1,835 |
18 | vocal-remover | 1,687 |
19 | mmrazor | 1,600 |
20 | pytorch-toolbelt | 1,556 |
21 | image-background-remove-tool | 1,510 |
22 | medicaldetectiontoolkit | 1,326 |
23 | sd-webui-inpaint-anything | 1,273 |