Awesome
Awesome-Segment-Anything
Tribute to Meta AI's Segment Anything Model (SAM)
A collection of projects, papers, and source code for SAM and related studies.
Keywords: Segment Anything Model, Segment Anything, SAM, awesome
CATALOGUE
Origin of the Study :heartpulse: Project & Toolbox :heartpulse: Lecture & Notes :heartpulse: Papers
1 Origin of the Study <span id='quick-start'></span>
Fundemental Models
2 Project & Toolbox<span id='tool'>
-
[Awesome Segment-Anything Extensions] Awesome Segment-Anything Extensions [paper][code]
-
[Awesome Anything] A curated list of general AI methods for Anything [paper][code]
-
[Awesome Segment Anything] Awesome Segment Anything [paper][code]
Preview | Project |
---|---|
[Grounded-Segment-Anything] Grounded-Segment-Anything(DINO + SAM) [paper][code] | |
[Grounded Segment Anything: From Objects to Parts] Support text prompt input(GLIP/VLPart + SAM)[paper][code] | |
[Semantic-Segment-Anything] A pipeline on top of SAM to predict semantic category for each mask [paper][code] | |
[GroundedSAM-zero-shot-anomaly-detection] Segment any anomaly[papaer][code] | |
[EditAnything] EditAnything [paper][code] | |
[sd-webui-segment-anything] extension for helping stable diffusion webui with inpainting [paper][code] | |
[SALT] Segment Anything Labelling Tool [paper][code] | |
[SAM-CLIP] Segment Anything CLIP [paper][code] | |
[Prompt-Segment-Anything] An implementation of SAM[parper][code] | |
[Count-Anything] Few-shot SAM Counting[parper][code] | |
[SegGPT: Vision Foundation Models] One touch for segmentation in all images (SAM+SegGPT)[paper][code] | |
[napari-segment-anything] Image viewer plugin of SAM[paper][code] | |
[OCR-SAM] SAM is applied to OCR [paper][code] | |
[SegDrawer] Simple static web-based mask drawer[paper][code] | |
[Magic Copy] Extract and copy foreground objects using SAM[paper][code] | |
[Track-Anything] Video object tracking and segmentation based on SAM[paper][code] | |
] | [SAM-Track] Video object tracking and segmentation based on SAM[paper][code] |
[Count Anything] Count any object[paper][code] | |
[Inpaint Anything] Inpaint Anything [paper][code] | |
[Transfer-Any-Style] Transfer-Any-Style[paper][code] | |
[Anything-3D] Anything-3D [paper][code] | |
[SEEM] Segment Everything Everywhere All at Once [paper][code] | |
[Caption-Anything] Generate descriptive captions for any object [paper][code] | |
[Caption-Anything] Generate descriptive captions for any object [paper][code] | |
[Image.txt] Transform Image Into Unique Paragraph [paper][code] | |
[3D-Box via Segment Anything] Extend the scope to 3D world [paper][code] | |
[SegmentAnyRGBD] Segment rendered depth images based on SAM [paper] [code] |
3 Lecture & Notes<span id='workshop'>
How to | roboflow how-to-segment-anything-with-sam [blog]
4 Papers <span id='papers-by-categories'></span>
Image Segmentation & Medical Image Segmentation
-
[Zero-shot Segmentation] Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging[paper][code]
-
[generic segmentation] Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications [paper][code]
-
[Medical Image segmentation] SAMM (Segment Any Medical Model): A 3D Slicer Integration to SAM [paper][code]
-
[Medical Image segmentation] SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Model [paper] [code]
-
[Camouflaged Object Segmentation] SAM Struggles in Concealed Scenes -- Empirical Study on "Segment Anything"[paper][code]
-
[Brain Extraction] Brain Extraction comparing Segment Anything Model (SAM) and FSL Brain Extraction Tool[paper][code]
Object Detection & Tracking
-
[Camouflaged Object Detection] Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection[paper][code]
-
[Multi-Object Tracking] CO-MOT[paper][code]
Explaning and Supporting Basic Models
- [CLIP] CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks [paper][code]
Arxiv-daily-update
Click here to check the daily-updated paper list!