Latest posts tagged with #segmentanything on Bluesky
Build Custom Image Segmentation Model Using YOLOv8 and SAM
Video explanation: youtu.be/8cir9HkenEY
Written explanation with code: eranfeit.net/segment-anyt...
Eran Feit
#Ultralytics #SegmentAnything #ImageSegmentation
The PlantSAM plant region detection and segmentation pipeline for herbarium images. Clockwise, starting at the top left: Each image is divided into patches, processed by YOLOv10 for plant region detection, and segmented by SAM. The segmented patches are then recombined to create a complete plant mask.
PlantSAM: An object detection-driven segmentation pipeline for herbarium specimens
New in #AppsPlantSci by Youcef Sklab, Florian Castanet, Hanane Ariouat, et al.
bsapubs.onlinelibrary.wiley.com/doi/full/10....
#botany #herbarium #deeplearning #digitization #SegmentAnything #objectdetection
Meta SAM 3 is now running inside Griptape Nodes.
Accurate object masks. Multi object detection. Video segmentation.
Perfect for inpainting, outpainting, and advanced creative workflows.
Watch how to set it up and use it: youtu.be/6ttZu7B0Zu0
#Griptape #AItools #ComputerVision #SegmentAnything
👉 Download the plugin here: github.com/opengeos/qgi...
💻 Full video tutorial: youtu.be/oPZc7BvDsHE
#QGIS #SegmentAnything #SAM #GeoAI #RemoteSensing
FloorSAM Applies Segment Anything Model for Accurate Floorplan Mapping
FloorSAM merges density maps with the Segment Anything Model to produce floorplans from LiDAR, improving accuracy and recall on Giblayout and ISPRS benchmarks. Read more: getnews.me/floorsam-applies-segment... #floorsam #segmentanything #floorplan
Three-panel image showing a UNet model applied to remote sensing imagery. Left: grayscale UNet output showing probability map of detected features, here trees. Center: input false-color infrared satellite image with vegetation coloured in reddish colours. Right: same input with bright green overlay showing segmented tree crown areas after thresholding.
🚀 Getting started with Deep Learning for remote sensing? Check out these beginner tutorials from FU Berlin: 🧠 UNet in PyTorch: bit.ly/3GBWPx1 🛰️ Segment Anything for GeoTIFFs: bit.ly/3GBWRVF 🌍 #DeepLearning #PyTorch #GeospatialAI #UNet #SegmentAnything #EarthObservation #OpenScience
Want to use Meta’s Segment Anything with #OpenSeadragon?
I finally wrote up a proper README for the #Annotorious plugin: 👉 github.com/annotorious/... Give it a try—and let me know what you build! #SegmentAnything #IIIF #Annotation
🔥 Our paper SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation is accepted as a #Highlight at #CVPR2025! 🎉
We make #SegmentAnything wiser, enabling it to understand textual prompts—training only 4.9M parameters! 🧠
💻 Code, models & demo: github.com/ClaudiaCutta...
Why SAMWISE?👇
Wait... is that a new button in #IMMARKUS? 🪄 Yes! Click the magic wand for automatic object selection, powered by #SegmentAnything. Just point, click, and let AI do the work! Try it out and let us know what you think. #DigitalHumanities #IIIF
Update: Smart object selection in zoomable images with #OpenSeadragon and #SegmentAnything! The next key challenge: Creating a seamless workflow—picking objects, refining shapes, and manually enhancing the outline. Stay tuned! #IMMARKUS #IIIF #DigitalHumanities #Maps
Next steps: #SegmentAnything in OpenSeadragon 🚀 Sort of, at least. There's no way around the ~2s wait for viewport encoding. But it still feels bearable—especially given the huge speed-up for complex shapes. Stay tuned!
Progress! Refine and extend areas by adding points to #SegmentAnything queries. Plus, polygon smoothing for cleaner annotation shapes. Next up: making it work in OpenSeadragon… #IMMARKUS #DigitalHumanities #Annotorious
Wow—this is #SegmentAnything 2 running *entirely* in the browser! With WebGPU (Chrome, Edge), generating embeddings took ~2s for a 1024x1024px region on my machine. No server required! #Annotation #DigitalHumanities #Maps #IIIF
Second day in Marburg : Erik Radisch from Sächsischen Akademie der Wissenschaften presents an integration of #SegmentAnything into #Annotorious
Website that gives you SUPERPOWER (Part 1). Create video cutouts and effects with a few clicks using AI for free using sam2.metademolab. 🤯
#meta #segmentanything #videoeffects #website #free #aiapp #aisoftware #videoeditingsoftware #aiwebsite #videoeditingtutorial #metaai
The image is a collage of three sections. The first row shows various cartoon-stylized fish. The second row depicts cartoon-stylized people in an indoor play area; one person is falling. The third row shows cartoon-stylized people walking
A colorful painting depicts multiple figures wearing traditional attire and white head coverings, set against a vibrant green background.
Updated version of #segmenteverygrain comes with an improved Unet model for prompting the #segmentanything model. These pebbles are being rounded by the waves at Torrey Pines State Beach in California https://github.com/zsylvester/segmenteverygrain
Couldn't refrain from experimenting a bit with #segmentanything to see how it could be used in the geosciences and I think its potential is significant. Here is an example of how labeling works on a thin section image from a Miocene sandstone (image from...
