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.
Official code "Taming SAM3 under Distribution Shift: ConceptBank for Support-Assisted Open-Vocabulary Segmentation"
Using C++ TensorRT for SAM3 model inference
Automated image & video captioning using Qwen-VL, Gemma4 and SAM3.
Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.
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
Interactive matte / roto tool for VFX – repairs damaged plate frames, generates alpha mattes for multiple objects (SAM3, CoTracker3, MatAnyone2, VideoMaMa, ViTMatte, LTX 2.5 Alpha Gen via ComfyUI), exports to Nuke and After Effects. REST API + CLI for AI agents. GPL-3.0.
Image Annotations tools integrated with sam 3
Remove objects and people from RAW photos with local AI, inside LightCraft (unofficial plug-in): SAM 3 selection, LaMa / SDXL / FLUX fills, written back into a RAW DNG.
CPU-optimised inference wrapper for Meta's SAM 3 — inference pipeline with chunked video processing, automatic object detection, and IoU-based tracking.
Efficient SAM3 (Segment Anything Model 3) inference from scratch in pure C — Metal GPU + multithreaded CPU, no Python dependencies
Generate editable scientific SVG figures from method text with local SAM3 and dual-provider routing.
ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3
One ComfyUI node: click a subject, get a generative-quality alpha with clean edges. SAM3 + LTX-2.5, native 4K, EXR out.
To associate your repository with the sam3 topic, visit your repo's landing page and select "manage topics."