Boyang Deng

Yay, finally! Introducing Vision Banana🍌 from @GoogleDeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: vision-banana.github.io (1/5)

Introducing CityRAG! We wanted video generative models to be grounded in the real world — if I’m in London, I want to look around and actually see Big Ben. CityRAG generates videos of cities featuring real buildings and roads, with arbitrary weather, people, and cars. 1/N page: cityrag.github.io paper: arxiv.org/abs/2604.19741

@taiyasaki @sherwinbahmani Congrats @sherwinbahmani ! Quite a milestone!

Congratulations Dr. @sherwinbahmani

Thrilled to announced that at #ICCV2025 we will host the first workshop on 𝐆𝐞𝐨𝐦𝐞𝐭𝐫𝐲-𝐅𝐫𝐞𝐞 𝐍𝐨𝐯𝐞𝐥 𝐕𝐢𝐞𝐰 𝐒𝐲𝐧𝐭𝐡𝐞𝐬𝐢𝐬 𝐚𝐧𝐝 𝐂𝐨𝐧𝐭𝐫𝐨𝐥𝐥𝐚𝐛𝐥𝐞 𝐕𝐢𝐝𝐞𝐨 𝐌𝐨𝐝𝐞𝐥𝐬 geofreenvs.github.io a.k.a. "3D Computer Vision in the era of Video Models" 😅

@songyoupeng @GordonWetzstein @Jimantha @StanfordAILab @GoogleDeepMind huggingface paper page: huggingface.co/papers/2504.08…

Work done w/ @songyoupeng, Kyle Genova, @GordonWetzstein, @Jimantha, Leonidas Guibas, and Thomas Funkhouser. This is a collaboration between @StanfordAILab and @GoogleDeepMind.

Curious about how cities have changed in the past decade? We use MLLMs to analyse 40 million Street View images to answer this. Do you know that "juice shops became a thing in NYC" and "miles of overpasses were painted BLUE in SF"? More at→boyangdeng.com/visual-chronic… (vid ↓ w/ 🔊)

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

🚀 Introducing CAT4D! 🚀 CAT4D transforms any real or generated video into dynamic 3D scenes with a multi-view video diffusion model. The outputs are dynamic 3D models that we can freeze and look at from novel viewpoints, in real-time!
Be sure to try our interactive viewer!

Symmetries are everywhere — from butterfly’s wings to Greek temples. But detecting them in noisy data? That’s a challenge. 🦋🏛 Our #SIGGRAPHAsia2024 paper, Robust Symmetry Detection via Riemannian Langevin Dynamics, tackles this: symmetry-langevin.github.io 🧵(1/n)

@songyoupeng @mapo1 @AutoVisionGroup Eccellente! Bravo!

Honored to receive the ECVA PhD Award at #ECCV24! This incredible PhD journey wouldn't have been possible without the tremendous support of two of my wonderful supervisors @mapo1 and @AutoVisionGroup! My deepest gratitude to you both❤️

@zhengqi_li @Jimantha @GordonWetzstein Meet us at SIGGRAPH 2024 (2pm July 29 at Mile High 1A). Arxiv: arxiv.org/abs/2407.13759. HF: huggingface.co/papers/2407.13….

@zhengqi_li @Jimantha @GordonWetzstein Music in video: grandbrothers.bandcamp.com/track/valentin… (please support the artist at bandcamp).

Thought about generating realistic 3D urban neighbourhoods from maps, dawn to dusk, rain or shine? Putting heavy snow on the streets of Barcelona? Or making Paris look like NYC? We built a Streetscapes system that does all these. See boyangdeng.com/streetscapes. (Showreel w/ 🔊 ↓)

Introducing Proteus 0.1, REAL-TIME video generation that brings life to your AI. Proteus can laugh, rap, sing, blink, smile, talk, and more. From a single image! Come meet Proteus on Twitch in real-time. ↓ Sign up for API waitlist: apparate.ai/early-access.h… 1/11

@docmilanfar Also, I found on the vinyl cover of this album that the guitar bit of a few tracks is done by the great Robert Fripp. Yet another reason to never miss this masterpiece. And there's Phill Collins on the drum.

@agarwl_ @EmtiyazKhan Oh, that's just you alone. Best Paper, here you go 🤪

@EmtiyazKhan What about ratingAvg >= 7?

Since many have asked, after discussion period at #NeurIPS2022, the rating distribution did change somewhat (for 100 papers) ratingAvg >=6: before 8, after 24 ratingAvg >=5: before 45, after 52 My own paper got pushed downward from 4,7,7 to 4,4,4 😭 (it's my best work in yrs)

@taiyasaki That BBS+Brembo combo is eye-catching 😎

RIP Shunji Tanaka #mazda #mx5 One hell of a designer!