Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

Adapting Segment Anything Model for Medical Image Segmentation

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2

The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"

RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)

Export Segment Anything Models to ONNX

[NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim

The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"

A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.

SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation

[IEEE TPAMI] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

Code for "Segment Anything Model for Medical Image Analysis: an Experimental Study" in Medical Image Analysis

[ACM TOMM] 🎉Wakeup-Darkness: When Multimodal Meets Unsupervised Low-light Image Enhancement

SegmentAnyBone: A Universal Model that Segments Any Bone at Any Location on MRI

CPU compatible fork of the official SAMv2 implementation aimed at more accessible and documented tutorials

An extension of 3D Slicer using the Segment Anything Model (SAM) to aid the segmentation of 3D data from tomography or other imaging techniques.

3D Slicer extension for Segment Anything Model (SAM) developed by Meta

[ICLR 2025] Official code of "Segment any 3D Object with Language"

This app integrates the Segment Anything Model (SAM) with Sentinel-2 data. The app is built using Dash Plotly and dash leaflet. It allows segmenting satellite images using the two ways provided by SAM: automatic mask generator and prompt segmentation (using points and bounding boxes).