Awesome-segment-anything-extensions

Segment-anything related awesome extensions/projects/repos/applications.

Welcome to starts ⭐ & comments 💹 & sharing 😀 !!

- 2023.4.9: Recent works/projects (from 2023) 
- welcome to add if any information misses. 😎

---

Recent Works

• Segment Anything Model (SAM) official Repo

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

• Grounded-Segment-Anything (Combination of Ground-DINO and Segment-Anything) Repo

• Segment-Any-Anomaly + (SAM + hybrid prompt regularization for zero-shot anomaly detection)ArXiV

• Segment Any Point Cloud Sequences (SAM for self-supervised learning on large-scale 3D point clouds) Repo ArXiv Page

  

• Segment-Any-Anomaly (SAM + GroudingDINO for anomaly detection)Repo

• Segment and Track Anything (SAM-Track) Repo ArXiv

• Inpaint/Remove/Fill-Anything (image inpainting meets sam) Repo

• SEEM: Segment Everything Everywhere All at Once Repo

• Roboflow Annotate Smart Polygon is a free, automated image annotation tool powered by Segment-Anything Blog, App

https://user-images.githubusercontent.com/870796/231829898-7219aba8-2931-42ae-82a4-9b2a91b02d0a.mp4

• Image Editing Anything (SAM + CLIP +StableDiffusion) Repo

• Semantic Segment Anything (SAM for semantic seg) Repo

• segment-anything-with-clip (SAM + CLIP) Repo

• magic-copy (use SAM for foreground mask segmentation) Repo

• EditAnything (SAM for image generation) Repo

• Prompt-Segment-Anything (use SAM for instance segmentation) Repo

• RefSAM (use SAM for refer image segmentation) Repo

• sam-mmrotate(use SAM for generating rotated bounding boxes with MMRotate) Repo

• Fast-SAM (fast segment-anything) repo

• Mobile-SAM (faster segment-anything) repo

• Disappear(use SAM for foreground removal) Repo

• Segment-anything-with-image-captioning(sam + image caption) Repo

• Open-vocabulary-Segment-Anything (OWL-ViT of Google + Segment Anything of Meta) Repo

• semantic drawing with Segment Anything Model (SAM for mask drawing/editing) Repo

• Annotation-anything-pipeline (GPT+SAM) Repo

• MOTSAM (MOT+SAM->MOTS)Repo

• SAMCOD (SAM for Camouflaged Object Detection) Paper Repo

• Segment Anything Model (SAM) in Napari (SAM + Napari) Repo

• inpainting-anything (SAM + inpainting) Repo

• segment-anything-eo (Earth observation tools for Meta AI Segment Anything) Repo

• Segment Anything for Stable Diffusion Webui (helping stable diffusion webui users to use segment anything to do stable diffusion inpainting) Repo

• Napari plugin of Segment Anything Model (SAM) [Repo] (https://github.com/JoOkuma/napari-segment-anything)

• segment-anything-and-name-it (Visual GPT + SAM) Repo

• AnyLabeling = LabelImg + Labelme + Improved UI + Auto-labeling Repo

• Caption-anything (Segment Anything + Visual Captioning + ChatGPT) Repo

• Segment-anything-u-specify (using sam + clip to segment anything u specify) Repo

• OCR-SAM (SAM for Text, Text Removal and Text Inpainting) Repo

• finetune-anything (fine-tuning of SAM ) Repo

• grounded-segment-anything-colab Repo

• SAM Medical Imaging Repo

• Segment Anything Prompt (SAM + GroundDINO + Stable Diffusion for foreground removal and background inpainting) Repo

• Transform Image Into Unique Paragraph (ChatGPT+SAM+BLIP) Repo

• LIME-SAM (SAM + Explainable Artificial Intelligence) Repo

• sam-with-mmdet (SAM+MMDetection) Repo

• open-tracking (sam + tracking) Repo

• 3D-Box via Segment Anything (sam for 3D Detection) Repo

• Anything-3D (Segment-Anything + 3D. Let's lift the anything to 3D) Repo

• Transfer-Any-Style (SAM for style transfer) Repo

• Paint-anything (sam for drawing) Repo

• track-anything (VOS + sam)Repo

• SAM-medical (SAM for medocal image segmentation)Repo

• relate-anything (relation empowered via SAM) Repo

• Count Anything (SAM for counting) Repo

• ShowAnything (SAM + SD for editing) Repo

• MedSAM (SAM for medicine, training tutorial) Repo

• Personalize-SAM (Personalize Segment Anything with 1 Shot in 10 Seconds) Repo

• Segment Any Moving Object with Moving Ego Vehicle (SAM for multi-object segmentation) arXiv

• Customized Segment Anything Model for Medical Image Segmentation (SAM+LoRA fot Medical Segmentation) ArXiv

• Instruct to Act (SAM+OpenCLIP for robotics application) Repo

• finetune-anything (SAM finetuning) Repo

• SAMScore (semantic Structural Similarity Metric for Image Translation Evaluation) ArXiv

• Detect-AnyShadow (SAM for shadow det) Repo

• SAD: Segment Any RGBD (SAM+Depth / SAM for RGBD) Repo

• SAM-HQ: Segment Anything in High Quality (High Quality Mask with SAM) Repo

• Calib-anything (SAM for calibration optimization) Repo

Relevant Repos

• Towards Segmenting Anything That Moves Repo

• SegGPT: Segmenting Everything In Context Repo

• Painter Repo

• Stable Diffusion (High-Resolution Image Synthesis with Latent Diffusion Models) Repo

• ControlNet (Adding Conditional Control to Text-to-Image Diffusion Models.) Repo Paper

• image2text powered by CLIP and BLIP Repo