pbonazzi/picosam3

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

[TMLR 26] EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

D-FINE-seg Object Detection and Segmentation Framework (Train, Export, Inference)

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Netspresso Trainer 2026: Train, Compress and Deploy Vision AI Models on Edge Devices

Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).