Tengda Han

Research Scientist @GoogleDeepMind. Previously PhD @Oxford_VGG

[Tengda Han @TengdaHan]

@jianyuan_wang @dimadamen 🚀

[Tengda Han @TengdaHan]

@Michael_J_Black Congrats Michael!!

[Tengda Han @TengdaHan]

Accepted by @CVPR #CVPR2026 🎉🎉 Congratulations @sherryx90099597

[Tengda Han @TengdaHan]

Human perception is active: we move around to see, and we see with intention. In our latest work "Seeing without Pixels", we find "how you see" (how the camera moves) roughly reveals "what you do" or "what you observe" -- and this connection can be easily learned from data.

[Tengda Han @TengdaHan]

Accepted by @CVPR #CVPR2026 🎉🎉

[Tengda Han @TengdaHan]

Human learns from unique data -- everyone's OWN life -- but our visual representations eventually align. In our recent work "Unique Lives, Shared World" @GoogleDeepMind, we train models with "single-life" videos from distinct sources, and study their alignment and generalisation.

[Google DeepMind @GoogleDeepMind]

Gemini 3.1 Pro is here.

We’ve significantly improved the model’s overall intelligence so it can solve tougher problems. 🧵

[Tengda Han @TengdaHan]

@TongPetersb Thanks for sharing! Nice blog!

[Sayna Ebrahimi @SaynaEbrahimi]

I’m looking for PhD students in Audio & Video for a Summer 2026 internship at Google DeepMind!

⚠️ Requirement: Prior publication in this area.

To apply, tell me the most critical research gap in AV understanding to see if we are a match! https://t.co/uKQnftKwpJ

[Tengda Han @TengdaHan]

A SOTA model on 4D reconstruction from @GoogleDeepMind! Amazing work from @ChuhanZhang5 and the team! It was so satisfactory to see these reconstruction results and I've been having a great experience using it

[Chuhan Zhang @ChuhanZhang5]

A SINGLE encoder + decoder for all the 4D tasks!
We release 🎯 D4RT (Dynamic 4D Reconstruction and Tracking).

📍 A simple, unified interface for 3D tracking, depth, and pose
🌟 SOTA results on 4D reconstruction & tracking
🚀 Up to 100x faster pose estimation than prior works

[Weidi Xie @WeidiXie]

🚀 Glad to share the exciting project — SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass! We explored the generation of 3D scenes with multiple assets from a single image. 🎉 ACCEPTED by 3DV 2026!!!

All resources have been open-sourced and publicly available!
📄 Paper: https://t.co/51GB5oTMZR
💻 Code: https://t.co/g7Z1VuTEla
🔗 Model: https://t.co/zam2NDL30z
🌐 WebPage: https://t.co/MGlUuLyHd9

#3DVision #AI #GenerativeAI #ComputerVision #3DV2026 #SceneGen

[joao carreira @joaocarreira]

Future AI models will learn predominantly post-deployment – to do the tasks of interest to each user. This will happen throughout an individual “life”. In a new paper https://t.co/BrH9FxBqG0 we lay out groundwork for this type of capabilities in the wild from a visual standpoint.

[Tengda Han @TengdaHan]

Work from @SaynaEbrahimi, myself, and @dilaragoekay, @goolygu, Maks Ovsjanikov, Iva Babukova, @DanielZoran_ , Viorica Patraucean, @joaocarreira , Andrew Zisserman and @dimadamen at @GoogleDeepMind.
Arxiv: https://t.co/8hm90TyGIQ

[Tengda Han @TengdaHan]

Human learns from unique data -- everyone's OWN life -- but our visual representations eventually align. In our recent work "Unique Lives, Shared World" @GoogleDeepMind, we train models with "single-life" videos from distinct sources, and study their alignment and generalisation.

[Tengda Han @TengdaHan]

Sherry is currently on the industry job market. Highly recommend!!

[Zihui (Sherry) Xue @sherryx90099597]

Excited to share our latest work! Grateful for the guidance from all my collaborators, and special thanks to Tengda for being such an amazing mentor during my internship @GoogleDeepMind 😊

[Tengda Han @TengdaHan]

@KevinQHLin @sherryx90099597 @dimadamen Thanks for reposting!

[Tengda Han @TengdaHan]

@ducha_aiki @sherryx90099597 @dimadamen Thank you Dmytro for reposting! Glad you like it :)

[Tengda Han @TengdaHan]

Project page for more details and qualitative examples: https://t.co/E8BDGIM0w0
Sherry will be at @NeurIPSConf this week! Catch her to chat more!

[Tengda Han @TengdaHan]

Human perception is active: we move around to see, and we see with intention. In our latest work "Seeing without Pixels", we find "how you see" (how the camera moves) roughly reveals "what you do" or "what you observe" -- and this connection can be easily learned from data.

[Tengda Han @TengdaHan]

Can you tell which action corresponds to which camera trajectory in the video above? Check out our paper for answers! Work done by our great intern Sherry Xue @sherryx90099597 at @GoogleDeepMind, and with Kristen Grauman, @dimadamen and Andrew Zisserman.
https://t.co/ukbMRfAkZk

[Tengda Han @TengdaHan]

A belated post for our ACMMM paper: we recognize and track animated characters for movie understanding tasks. Great work from Zhongrui Gui, also with @JunyuXieArthur @WeidiXie and Andrew Zisserman from @Oxford_VGG .
Project page with code and dataset: https://t.co/G70041InQ8

[Tengda Han @TengdaHan]

Animated movies can be effortlessly understood by young minds, but appear to be challenging for video-language models, why? The key problem is the huge diversity of animated characters -- their appearance ranges from human-like faces, to cars, fish, blobs, etc.