sam3

Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models such as YOLO, FastVLM, and more.

Export and run SAM, MobileSAM, EfficientSAM, SAM 2/2.1, and SAM 3 as ONNX for portable image segmentation

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

[CVPR 2026] OccAny: Generalized Unconstrained Urban 3D Occupancy. The first Unified Framework for Generalized 3D Occupancy Prediction. Supports SAM2/SAM3, MUSt3R & Depth Anything 3.

Using C++ TensorRT for SAM3 model inference

Automated image & video captioning using Qwen-VL, Gemma4 and SAM3.

Official code "Taming SAM3 under Distribution Shift: ConceptBank for Support-Assisted Open-Vocabulary Segmentation"

The repository provides code for running inference with the Meta Segment Anything Model 3 (SAM 3).

Use Segment Anything 3 to label data for use with Autodistill.

Turn street photos into GPS coordinates using AI

Image Annotations tools integrated with sam 3

CPU-optimised inference wrapper for Meta's SAM 3 — inference pipeline with chunked video processing, automatic object detection, and IoU-based tracking.

Generate editable scientific SVG figures from method text with local SAM3 and dual-provider routing.

Efficient SAM3 (Segment Anything Model 3) inference from scratch in pure C — Metal GPU + multithreaded CPU, no Python dependencies

ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation

SAM3: Segment Anything Model 3 is an experimental, multi-functional computer vision application that provides a unified interface for text-conditioned and click-interactive segmentation. Built around Meta's advanced facebook/sam3 multi-model architecture.

Intelligent FFMPEG agent node for ComfyUI - transforms natural language video editing prompts into automated video transformations

Official code "Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation"

[MICCAI 2026] Official repository for “Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation”