Kris Kitani

Associate Research Professor at @SCSatCMU, @CMU_Robotics. Computer Vision, Machine Learning and Accessibility.

[CMU Center for Perceptual Computing and Learning @roboVisionCMU]

20+ new papers from CMU at CVPR 2026!!!
https://t.co/AtBMhz6qL1

[Kris Kitani @kkitani]

A snapshot into how SAM 3D Body is being used at CMU for assisting physical therapy

[AI at Meta @AIatMeta]

SAM 3D is helping advance the future of rehabilitation.

See how researchers at @CarnegieMellon are using SAM 3D to capture and analyze human movement in clinical settings, opening the doors to personalized, data-driven insights in the recovery process.

🔗 Learn more about SAM 3D: https://t.co/WAtASpkTdY

[Pablo Vela @pablovelagomez1]

Sam3 + Body is freaking amazing. I'm in the process of building an open-source @rerundotio and @Gradio demo that is similar to what Meta provided. Got the basic functionality up and running, now I need to hook it up to a Gradio interface. It's a really good model

[Kris Kitani @kkitani]

Use 3DB for better camera control! Uni3C + SAM 3D: The Ultimate Workflow for AI Camera Control|3D Motion wi... https://t.co/Q8m0xFPQG1 via @YouTube

[kk@study @kk_design_dev]

RustDesk神すぎる… 添付は流行りの3Dモデリングできるsam-3d-bodyで星街さんをWindowsで3D化しMacのBlenderで表示したもの
Mac Loveの私にはWindows環境は辛すぎるのでMac で Windows実機をP2Pでそのまま操作できるのがありがたすぎます

キーバインドでctrlを⌘キーにもできるので画面スワイプしながらMacの1画面として操作できる神ツール
ずっとMagic Trackpadで操作したかったのです...

ちなみにsam-3d-bodyはwindowsだとEGL、detectron2の問題で実行できないので(多分) detectをカットするので本来のパワーを発揮できないのですが実際のobjとして生成自体は可能でした

素の人体模型になってしまうので取り扱いがちょっとむつかしい

[Kris Kitani @kkitani]

@wildmindai Awesome!

[KANA @KanaWorks_AI]

SAM 3D × NanoBanana2 × Kling = 位置コントロール 🐰❤️‍🔥
ワークフロー：
1️⃣ SAM 3D Objects でモチーフを3D化
2️⃣ 好きな順番・配置に並び替える
3️⃣ Nano Banana 2 で新しい画像を生成
4️⃣ 仕上げに Kling で前後フレームの動画化
結果は——
✨位置の再現精度ほぼ90％！✨
🐰❤️‍🔥心臓バクバクしました。これは本当にすごい！！新しい創作の自由そのものです。
2025.11.21
@AIatMeta @GeminiApp @Kling_ai
#MetaAI #klingai #SAM3D #NanoBanana2 #kanaworksai

[CMU School of Computer Science @SCSatCMU]

Kris Kitani, faculty in @CMU_Robotics, led the development of SAM3D Body, which could transform physical therapy with AI pose estimation. SAM 3D Body delivers precise, AI-driven static position analysis to personalize rehabilitation and enhance patient outcomes.

[Kris Kitani @kkitani]

@_georgebaran @DennisAnthony__ Use “SAM 3D Body” to get a specialized person mesh https://t.co/K3ZpyNWYHA
There are actually two SAM 3D models

[Angry Tom @AngryTomtweets]

Transforming physical therapy with AI pose estimation. SAM 3D Body delivers precise, AI-driven static position analysis to personalize rehabilitation and enhance patient outcomes.

[KANA @KanaWorks_AI]

SAM 3D × Nano Banana × Kling × Domo のコンボが楽しすぎる…！🐰🤓
指定した人物を好きなアングル＆ポーズで3D化 →
動画生成 →
そのまま画風チェンジまで
一気通貫でいけるのヤバい🤣
本当に「自分専用の3D＆動画スタジオ」って感じ。
2025.11.20
@AIatMeta @Kling_ai @DomoAI_
#SAM3D #NanoBanana #DomoAI #AI動画 #kanaworksai #MetaAI #klingai #KlingLab

[KANA @KanaWorks_AI]

Meta AI のSAM 3D ｜テスト②
SAM 3D Body
これはもう狂ってるレベル😱🥳🍻
・単一画��→全身の形＆ポーズを3D再構築
・一部が隠れていてもちゃんと補完
・人物の変形＆インタラクション向き
2025.11.20
@AIatMeta　
#SAM3D #MetaAI #3Dモデリング #Blender #ゲーム開発 #b3d #kanaworksai

[Nicolas Ugrinovic @nicougrinovic]

📢 Recover highly accurate full-body pose and shape with perfect 2D alignment!

Very excited to finally share SAM 3D Body, work done at Meta!

Tech report: https://t.co/WdoxkxLP5e
Demo: https://t.co/24oQq21326
Blog: https://t.co/CUrMtAl2Lz

[AI at Meta @AIatMeta]

We’re sharing model checkpoints, an evaluation benchmark, human body training data, and inference code with the community to support creative applications in fields like robotics, interactive media, science, sports medicine, and beyond.

🔗 SAM 3D Body: https://t.co/rCwYQmEePr

🔗 SAM 3D Objects: https://t.co/GANYBpIR5z

[AI at Meta @AIatMeta]

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models:

🛋️ SAM 3D Objects for object and scene reconstruction

🧑‍🤝‍🧑 SAM 3D Body for human pose and shape estimation

Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions.

🔗 Learn more: https://t.co/yXcvts8Ogc

[CMU Center for Perceptual Computing and Learning @roboVisionCMU]

New model from Meta, SAM 3D Body, powered by people from Smith Hall (@kkitani,@jinkuncao, David Park, Jyun-Ting Song) of course! #goSmithHall

Introducing SAM 3D: a New Standard for 3D Object & Human Reconstruction ... https://t.co/G7whjw3Yg1 via @YouTube

[Kris Kitani @kkitani]

Super excited to share the release of SAM 3D. It's been a year in the making. Two models for lifting object and people to 3D!

[AI at Meta @AIatMeta]

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models:

🛋️ SAM 3D Objects for object and scene reconstruction

🧑‍🤝‍🧑 SAM 3D Body for human pose and shape estimation

Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions.

🔗 Learn more: https://t.co/yXcvts8Ogc

[Yitang Li @li_yitang]

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 https://t.co/3VdyRWgOqb

🧩ONE latent space for ALL tasks
⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy
🤖Natural recovery & transition

[Rohan Choudhury @rchoudhury997]

Excited to release our new preprint - we introduce Adaptive Patch Transformers (APT), a method to speed up vision transformers by using multiple different patch sizes within the same image!

[AI at Meta @AIatMeta]

To help fuel new research in the community around video learning and egocentric perception, together with the Ego4D consortium we’ve published a new research paper covering our work on Ego-Exo4D.

Access the full paper ➡️ https://t.co/OEOeedKYlu