#segmentanything

Stefan Ihringercompfu@mograph.social
2025-04-28

I'd love to work on shows where SAM2 is good enough. But we have actors with fine hair detail and the comps need to survive 4K inspection so.... Indian roto vendors it is :-/

floss.social/@kdenlive/1144169

There's a #SegmentAnything toolset for #Nuke: github.com/Theo-SAMINADIN-td/N

It works but the lack of temporal stability makes it break down when actors are not moving. All the cool test footage is people running or objects moving around which is much more forgiving.

2025-04-11

Want to use Meta’s Segment Anything with #OpenSeadragon?
I finally wrote up a proper README for the #Annotorious plugin: 👉 github.com/annotorious/plugin- Give it a try—and let me know what you build! #SegmentAnything #IIIF #Annotation

2025-03-06

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

2025-03-04

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

2025-02-27

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 annotating complex shapes. Stay tuned!

2025-02-27

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

2025-02-19

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

David Masondn_mason@mas.to
2024-03-20

I am honestly floored at the #SegmentAnything implementation for #ImageJ / #Fiji

Even running on a laptop, once loaded, it's incredibly quick.

Moreover, it's a super-simple install which is a major barrier to many #AI #DeepLearning implementations.

Time to play around with some #Microscopy and #DigitalPathology data!

Details here: github.com/segment-anything-mo
Photo source: pexels.com/photo/photo-of-rail

2023-12-22

"Segment Anything as a Service" shared our approach to making advanced AI tools accessible and enhancing workflows cost-effectively with the Segment Anything Model. #segmentanything #AI #machinelearning #geospatial
🔗 developmentseed.org/blog/2023-

2023-12-22

"Exploring the Potential of the Segment Anything Model" highlighted innovative strides in AI, pushing boundaries in data annotation and satellite imagery. #segmentanything #machinelearning #computervision
🔗 developmentseed.org/blog/2023-

John Lister - GeoScrubGeoScrubJohnL@fosstodon.org
2023-11-26

Video series and article coming soon leveraging the brilliant Segment Geospatial to create a workflow for effectively creating mask datasets for training a U-Net model #SegmentAnything #Meta #GIS #GISChat #technology

Christian A. Schillerc_a_schiller@mastodon.online
2023-10-16

I'm proud to have published my first scientific paper as preprint on arXiv! arxiv.org/abs/2310.08683

I investigated the use of augmented reality for reinforcement learning agents by integrating Meta Research's SAM (Segment Anything) zero-shot model into the RL training data pipeline. Like equipping a virtual entity (the RL agent) with AR goggles.

#datascience #machinelearning #artificialintelligence #augmentedreality #reinforcementlearning #arxiv #atari #videogame #metaresearch #segmentanything

A reinforcement learning agent wearing augmented reality glasses playing atari video gamesarXiv paper "Virtual Augmented Reality for Atari Reinforcement Learning"
2023-08-16

Segment-geospatial v0.9.1 is out. It now supports segmenting remote sensing imagery with the High-Quality Segment Anything Model (HQ-SAM)

Video: youtu.be/n-FZzKirE9I
Notebook: samgeo.gishub.org/examples/inp
GitHub: github.com/opengeos/segment-ge

#segmentanything #geospatial #deeplearning

2023-08-13

Does anyone know of open source projects that use AI to segment orthorectified imagery and try to categorise bicycle paths or other cycling infrastructure, and check if they’re missing from OpenStreetMap?

I’m thinking of whether it would be possible to run Meta’s Segment Anything model over suitably licensed aerial imagery to find infra missing on OSM. Any thoughts/comments very welcome!

#openstreetmap #meta #segmentanything #ai #computervision #geospatial #gis #cycling #bikes #bicycles

2023-08-11

The recording of my presentation at the TensorFlow Working Group at SERVIR

Title: Automated Segmentation of Remote Sensing Imagery with the Segment Anything Model
Video: youtube.com/watch?v=45NpHeq1X6
Slides: bit.ly/TFWG
GitHub: github.com/opengeos/segment-ge

#segmentanything #geospatial #opensource #SERVIR

2023-08-07

Segment-geospatial v0.9.0 is out📢It now supports segmenting remote sensing imagery with box prompts. You can create box prompts interactively or use existing vector data as box prompts 🌐

GitHub: github.com/opengeos/segment-ge
Notebook: samgeo.gishub.org/examples/box
Video tutorial: youtu.be/ayFgAj23BfI

#geospatial #segmentanything #deeplearning

2023-06-29

DevSeed has now integrated DS-Annotate with the Segment Anything Model. This powerful tool enables swift and efficient annotation of map features, streamlining our processes significantly. This advancement wouldn't have been possible without our collaborative work with Ruben Mendoza, Ryan Avery, Wille Marcel, and Nick Ingalls.

#Geospatial #AI #Mapping #OSM #Sentinel2 #DevelopmentSeed #DSAnnotate #SegmentAnything #DataScience #osm #annotation #machinelearning #labeling #datateam #Meta #SAM #IA

2023-05-24

Segment-geospatial v0.8.0 is out. New features include segmentating remote sensing imagery with text prompts interactively 🤩

Notebook: samgeo.gishub.org/examples/tex
GitHub: github.com/opengeos/segment-ge
Video: youtu.be/cSDvuv1zRos

#geospatial #segmentanything

Yes!Onlineyesonline
2023-05-17

RT @giswqs: Segmenting remote sensing imagery with input prompts from existing files
GitHub: t.co/KUOhmJz8hs
Docs: t.co/UbkLx9c2l0
Notebook: t.co/EM2j6fHmhU

t.co/W6byeZSLzt

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst