Yihang Luo retweeted
What if you could step inside a painting? We use Mundo to imagine new viewpoints from a single image of Raphael’s fresco, The School of Athens.
Yihang Luo retweeted
🎥Reshoot a video from a camera that was never there~
Excited to share #Holo4D, accepted to #neurips2026 !
Give it a video and a new camera path: Holo4D lifts the video into 3D tracks and uses them to steer a video model. The camera moves; what happened stays the same. 🧵
Yihang Luo retweeted
What if you could step inside a van Gogh painting?
We used Mundo to imagine new viewpoints from a single painting.
Take a look at this short demo.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Yihang Luo retweeted
👋 What if you could turn your own environment into a programmable world—one you can explore, edit, and interact with? 🌍
Excited to introduce Mundo, our customized world model that brings this vision to life! Amazing work led by @onelineluo!
Given a few context views, a VLM agent builds and programs a 3D proxy world; code controls its state, physics simulates its dynamics, and a video generation model renders the results.
Mundo enables spatiotemporal exploration, precise interactions, and physically grounded simulations—all driven by code.
More broadly, agentic generation could be the next major paradigm for world models and controllable video generation, unlocking parameterized control and physically grounded interactions. 🚀
🌍 Introducing Mundo, led by my student @onelineluo: a customized world model that turns images of a place into an environment for exploration, editing, and simulation.
Explore new viewpoints, change objects and physical properties, or simulate robot navigation and manipulation — all within the captured environment.
The key is an explicit, editable world state: code specifies actions, physics computes their consequences, and a video model renders the outcome using the input images as visual context.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Code coming soon!
We’ve built a customizable world model that turns just a few photos into an interactive virtual environment.
Let's transform real-world scenes directly into virtual spaces ready for exploration and manipulation!
Project: mundo-world-model.github.io
Blog: huggingface.co/blog/Luo-Yiha…
Yihang Luo retweeted
🌍 Introducing Mundo, led by my student @onelineluo: a customized world model that turns images of a place into an environment for exploration, editing, and simulation.
Explore new viewpoints, change objects and physical properties, or simulate robot navigation and manipulation — all within the captured environment.
The key is an explicit, editable world state: code specifies actions, physics computes their consequences, and a video model renders the outcome using the input images as visual context.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Code coming soon!
Yihang Luo retweeted
This is why I refuse to work on camera estimation problems. For embodied AI, I consider it a **solved** problem at large – there are better things to spend your time on.
It's only a "problem" in academia.
Yihang Luo retweeted
Introducing 𝗦𝗧𝗿𝗲𝗮𝗺𝟯𝗥, a new 3D geometric foundation model for efficient 3D reconstruction from streaming input. Similar to LLMs, STream3R uses casual attention during training and KVCache at inference.
No need to worry about post-alignment or reconstructing from scratch. You can easily add new frames and update the reconstruction incrementally. Great work by Yushi @GROS17121524 and Yihang @TheYihangLuo !
Project: nirvanalan.github.io/project…
arXiv: arxiv.org/abs/2508.10893
Code: github.com/NIRVANALAN/STream…
See a streaming reconstruction of our S-Lab lobby below!
🔥Streaming-based 3D/4D Foundation Model🔥
We present STream3R, which reformulates dense 3D/4D reconstruction into a sequential registration task with **causal attention**.
- Projects: nirvanalan.github.io/project…
- Code: github.com/NIRVANALAN/STream…
- Model: huggingface.co/yslan/STream3…
Yihang Luo retweeted
🔬 Our study introduces "Upscale-A-Video," a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence locally & globally, balancing fidelity and quality.
🚀 Project page: shangchenzhou.com/projects/u…
💻 GitHub: github.com/sczhou/Upscale-A-…
🎥 Video: youtu.be/b9J3lqiKnLM
@ShangchenZhou @peiqing001 @Iceclearwjy @TheYihangLuo
Yihang Luo retweeted
Our #ProPainter👨🎨 @huggingface demo is finally live! Remove any object with just a click. Dive in and give it a try! 🛹
Access the demo here: huggingface.co/spaces/sczhou…
#ICCV2023 Introducing 𝐏𝐫𝐨𝐏𝐚𝐢𝐧𝐭𝐞𝐫 🔥 again – our new solution for video inpainting🎨. Use it for object removal and seamless video completion. Feel free to try it out!
Project: shangchenzhou.com/projects/P…
Github: github.com/sczhou/ProPainter
Paper: huggingface.co/papers/2309.0…
Yihang Luo retweeted
🌟Do you feel these bright spots quite annoying in smartphone photography?
🌟Our highlight paper proposes the first learning-based method specialized for this problem. Come and check in this afternoon #CVPR2023 !
📍 Location: West Exhibit Hall #17
⏰ Time: 04:30 PM - 06:30 PM

















