Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!
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
Tailor是一款视频智能裁剪、视频生成和视频优化的视频剪辑工具。目前的目标是通过人工智能技术减少视频剪辑的繁琐操作，让普通人也能简单实现专业剪辑人的水准！长远目标是让视频剪辑实现真正的AIGC！
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.
[CVPR 2025] Code for Segment Any Motion in Videos
SimpleAICV:pytorch training examples.
Export and run SAM, MobileSAM, EfficientSAM, SAM 2/2.1, and SAM 3 as ONNX for portable image segmentation
The code for PixelRefer & VideoRefer
Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.
[CVPR 2026] OccAny: Generalized Unconstrained Urban 3D Occupancy. The first Unified Framework for Generalized 3D Occupancy Prediction. Supports SAM2/SAM3, MUSt3R & Depth Anything 3.
Grounded Tracking for Streaming Videos
[CVPR'26 Highlight] Official Code for “V²-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence”
An open-source studio for prompt-driven video segmentation. Powered by SAM2 & Grounding DINO with a hybrid Cloud-Local architecture.
Playground Web UI using segment-anything-2 models from the Meta.
A cutting-edge deep learning project that combines YOLOv11 (for real-time object detection) with SAM2 (Segment Anything Model) to accurately detect and segment tumors in medical images. Designed for high precision in healthcare diagnostics and research applications.
A skill tool for Codex and Claude Code that converts images, PDFs, and image-based PPTX files into editable PowerPoint presentations.
Zero-shot segmentation of very large remote sensing images with SAM2: multi-pass coverage maximization and parameter-free tile-boundary merging (Remote SAMsing)
[CVPR 2026] Official repository for "SAMIX: Reinforcing SAM2 with Semantic Adapter and Reference Selecting Policy for Mix-Supervised Segmentation"
To associate your repository with the sam2 topic, visit your repo's landing page and select "manage topics."