Reminder: Annotorious brings Photoshop-like selection tools to your browser!
• Intelligent Scissors
• Magnetic Cursor
• WebGPU-powered SegmentAnything
I just wrote proper docs! Usage guides, examples, full API:
github.com/annotorious/...
github.com/annotorious/...
#OpenSeadragon #IIIF
• Intelligent Scissors
• Magnetic Cursor
• WebGPU-powered SegmentAnything
I just wrote proper docs! Usage guides, examples, full API:
github.com/annotorious/...
github.com/annotorious/...
#OpenSeadragon #IIIF
August 8, 2025 at 10:40 AM
Reminder: Annotorious brings Photoshop-like selection tools to your browser!
• Intelligent Scissors
• Magnetic Cursor
• WebGPU-powered SegmentAnything
I just wrote proper docs! Usage guides, examples, full API:
github.com/annotorious/...
github.com/annotorious/...
#OpenSeadragon #IIIF
• Intelligent Scissors
• Magnetic Cursor
• WebGPU-powered SegmentAnything
I just wrote proper docs! Usage guides, examples, full API:
github.com/annotorious/...
github.com/annotorious/...
#OpenSeadragon #IIIF
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
February 19, 2025 at 3:36 PM
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
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
March 6, 2025 at 12:26 PM
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
March 4, 2025 at 10:41 AM
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
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
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
GitHub - annotorious/plugin-segment-anything: A smart polygon selection tool based on SegmentAnything 2.
A smart polygon selection tool based on SegmentAnything 2. - annotorious/plugin-segment-anything
github.com
April 11, 2025 at 7:42 AM
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
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
SAMURAI is a new model for visual object tracking published by the University of Washington. It improves on Meta's SegmentAnything 2. Project page: yangchris11.github.io/samurai/
#computervision #objecttracking
#computervision #objecttracking
November 24, 2024 at 9:44 AM
SAMURAI is a new model for visual object tracking published by the University of Washington. It improves on Meta's SegmentAnything 2. Project page: yangchris11.github.io/samurai/
#computervision #objecttracking
#computervision #objecttracking
👉 Download the plugin here: github.com/opengeos/qgi...
💻 Full video tutorial: youtu.be/oPZc7BvDsHE
#QGIS #SegmentAnything #SAM #GeoAI #RemoteSensing
💻 Full video tutorial: youtu.be/oPZc7BvDsHE
#QGIS #SegmentAnything #SAM #GeoAI #RemoteSensing
GitHub - opengeos/qgis-samgeo-plugin: QGIS plugin for the SamGeo Python package
QGIS plugin for the SamGeo Python package. Contribute to opengeos/qgis-samgeo-plugin development by creating an account on GitHub.
github.com
December 9, 2025 at 7:12 PM
👉 Download the plugin here: github.com/opengeos/qgi...
💻 Full video tutorial: youtu.be/oPZc7BvDsHE
#QGIS #SegmentAnything #SAM #GeoAI #RemoteSensing
💻 Full video tutorial: youtu.be/oPZc7BvDsHE
#QGIS #SegmentAnything #SAM #GeoAI #RemoteSensing
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
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
December 15, 2025 at 4:24 PM
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
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
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!
February 27, 2025 at 12:03 PM
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
February 27, 2025 at 8:49 AM
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
🚀 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
July 22, 2025 at 8:08 AM
🚀 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
Second day in Marburg : Erik Radisch from Sächsischen Akademie der Wissenschaften presents an integration of #SegmentAnything into #Annotorious
December 13, 2024 at 9:27 AM
Second day in Marburg : Erik Radisch from Sächsischen Akademie der Wissenschaften presents an integration of #SegmentAnything into #Annotorious
🔥 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?👇
We make #SegmentAnything wiser, enabling it to understand textual prompts—training only 4.9M parameters! 🧠
💻 Code, models & demo: github.com/ClaudiaCutta...
Why SAMWISE?👇
April 10, 2025 at 6:07 PM
🔥 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?👇
We make #SegmentAnything wiser, enabling it to understand textual prompts—training only 4.9M parameters! 🧠
💻 Code, models & demo: github.com/ClaudiaCutta...
Why SAMWISE?👇
(Honestly, it kind of blows me away that we've gone from struggling with "Is this an 'A' ?" to SegmentAnything, StableDiffusion, ChatGPT, etc in just a decade!)
March 20, 2025 at 8:07 PM
(Honestly, it kind of blows me away that we've gone from struggling with "Is this an 'A' ?" to SegmentAnything, StableDiffusion, ChatGPT, etc in just a decade!)
📦 facebookresearch / segment-anything
⭐ 50,861 (+23)
🗒 Jupyter Notebook
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.
⭐ 50,861 (+23)
🗒 Jupyter Notebook
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.
GitHub - facebookresearch/segment-anything: 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.
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. -...
github.com
July 16, 2025 at 10:02 PM
📦 facebookresearch / segment-anything
⭐ 50,861 (+23)
🗒 Jupyter Notebook
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.
⭐ 50,861 (+23)
🗒 Jupyter Notebook
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.
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
#meta #segmentanything #videoeffects #website #free #aiapp #aisoftware #videoeditingsoftware #aiwebsite #videoeditingtutorial #metaai
November 14, 2024 at 7:54 AM
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
#meta #segmentanything #videoeffects #website #free #aiapp #aisoftware #videoeditingsoftware #aiwebsite #videoeditingtutorial #metaai
Yeah, there are quite a few public domain image archives (LoC, NYPL, PICRYL, PDIA, etc). I wanted to try making an automated pipeline that uses the Segmant Anything Model to auto-detect and auto-clip interesting image segments to stick in an image pool, and then automatically describe and tag them.
GitHub - facebookresearch/segment-anything: The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example no...
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. -...
github.com
July 10, 2026 at 6:11 PM
Yeah, there are quite a few public domain image archives (LoC, NYPL, PICRYL, PDIA, etc). I wanted to try making an automated pipeline that uses the Segmant Anything Model to auto-detect and auto-clip interesting image segments to stick in an image pool, and then automatically describe and tag them.
今日のGitHubトレンド
facebookresearch/segment-anything
このリポジトリは、Meta AI Researchが開発した、プロンプトに基づいて画像内のオブジェクトを高品質にセグメント化する汎用モデルSegment Anything Model (SAM) の研究成果、コード、関連リソースを公開することを目的としています。
点やボックスなどの入力からオブジェクトマスクを生成します。
また、画像と動画に対応した次世代モデルSAM 2についても案内しています。
facebookresearch/segment-anything
このリポジトリは、Meta AI Researchが開発した、プロンプトに基づいて画像内のオブジェクトを高品質にセグメント化する汎用モデルSegment Anything Model (SAM) の研究成果、コード、関連リソースを公開することを目的としています。
点やボックスなどの入力からオブジェクトマスクを生成します。
また、画像と動画に対応した次世代モデルSAM 2についても案内しています。
GitHub - facebookresearch/segment-anything: 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.
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. - fa
github.com
July 18, 2025 at 11:17 AM
今日のGitHubトレンド
facebookresearch/segment-anything
このリポジトリは、Meta AI Researchが開発した、プロンプトに基づいて画像内のオブジェクトを高品質にセグメント化する汎用モデルSegment Anything Model (SAM) の研究成果、コード、関連リソースを公開することを目的としています。
点やボックスなどの入力からオブジェクトマスクを生成します。
また、画像と動画に対応した次世代モデルSAM 2についても案内しています。
facebookresearch/segment-anything
このリポジトリは、Meta AI Researchが開発した、プロンプトに基づいて画像内のオブジェクトを高品質にセグメント化する汎用モデルSegment Anything Model (SAM) の研究成果、コード、関連リソースを公開することを目的としています。
点やボックスなどの入力からオブジェクトマスクを生成します。
また、画像と動画に対応した次世代モデルSAM 2についても案内しています。
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
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
Getting Started with Meta Segment Anything Model 3 in Griptape Nodes
In this video, we'll walk you through how to use Meta's Segment Anything Model 3 inside Griptape Nodes. This is the third generation of Meta's powerful image segmentation system and it delivers…
youtu.be
December 10, 2025 at 9:29 PM
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
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
「M5Stack LLM モジュール」
・オフライン環境でLLM（大規模言語モデル）の活用が可能
・搭載機能：KWS（ウェイクワード）、ASR （音声認識）、LLM（大規模言語モデル）、 TTS （テキスト音声合成）
・対応予定：Qwen2.5-1.5B、Llama3.2-1B、InternVL2-1B モデル、 CLIP、YoloWorld、DepthAnything、SegmentAnything
価格（消費税込み） 9,482 円
prtimes.jp/main/html/rd...
・オフライン環境でLLM（大規模言語モデル）の活用が可能
・搭載機能：KWS（ウェイクワード）、ASR （音声認識）、LLM（大規模言語モデル）、 TTS （テキスト音声合成）
・対応予定：Qwen2.5-1.5B、Llama3.2-1B、InternVL2-1B モデル、 CLIP、YoloWorld、DepthAnything、SegmentAnything
価格（消費税込み） 9,482 円
prtimes.jp/main/html/rd...
M5Stack社新製品、オフライン環境でLLMの活用を可能にする「M5Stack LLM モジュール」をスイッチサイエンスウェブショップにて2025年1月15日より販売開始
株式会社スイッチサイエンスのプレスリリース（2025年1月15日 15時07分）M5Stack社新製品、オフライン環境でLLMの活用を可能にする「M5Stack LLM モジュール」をスイッチサイエンスウェブショップにて2025年1月15日より販売開始
prtimes.jp
January 16, 2025 at 1:24 PM
「M5Stack LLM モジュール」
・オフライン環境でLLM（大規模言語モデル）の活用が可能
・搭載機能：KWS（ウェイクワード）、ASR （音声認識）、LLM（大規模言語モデル）、 TTS （テキスト音声合成）
・対応予定：Qwen2.5-1.5B、Llama3.2-1B、InternVL2-1B モデル、 CLIP、YoloWorld、DepthAnything、SegmentAnything
価格（消費税込み） 9,482 円
prtimes.jp/main/html/rd...
・オフライン環境でLLM（大規模言語モデル）の活用が可能
・搭載機能：KWS（ウェイクワード）、ASR （音声認識）、LLM（大規模言語モデル）、 TTS （テキスト音声合成）
・対応予定：Qwen2.5-1.5B、Llama3.2-1B、InternVL2-1B モデル、 CLIP、YoloWorld、DepthAnything、SegmentAnything
価格（消費税込み） 9,482 円
prtimes.jp/main/html/rd...
Codepen: codepen.io/fand/pen/ZYL...
ObjectStretch with SegmentAnything + VFX-JS
...
codepen.io
July 9, 2026 at 9:27 PM
Codepen: codepen.io/fand/pen/ZYL...
楽譜で試すなどしてみる．見開きは取れるけど，プロンプトを工夫してもページは取れない．惜しい．簡単な後処理で分割はできそうではある．
SegmentAnythingでPos/Neg指定してあげたほうがお手軽かもしれない？
SegmentAnythingでPos/Neg指定してあげたほうがお手軽かもしれない？
July 6, 2024 at 3:06 AM
楽譜で試すなどしてみる．見開きは取れるけど，プロンプトを工夫してもページは取れない．惜しい．簡単な後処理で分割はできそうではある．
SegmentAnythingでPos/Neg指定してあげたほうがお手軽かもしれない？
SegmentAnythingでPos/Neg指定してあげたほうがお手軽かもしれない？
detailed segmented regional information provided by pre-trained segmentation models (such as DeepLab, SegmentAnything and PSPnet), with Bayesian inference employed to enhance the manipulation localization. Experimental results demonstrate the [5/6 of https://arxiv.org/abs/2505.23586v1]
May 30, 2025 at 6:15 AM
detailed segmented regional information provided by pre-trained segmentation models (such as DeepLab, SegmentAnything and PSPnet), with Bayesian inference employed to enhance the manipulation localization. Experimental results demonstrate the [5/6 of https://arxiv.org/abs/2505.23586v1]