Shenlong Wang

@ShenlongWang

Assistant Professor at @IllinoisCS; 3D Computer Vision and Robot Perception.

shenlong.web.illinois.edu

Joined May 2010

461 Following

1,653 Followers

Replies Reposts Media

Shenlong Wang
@ShenlongWang
Oct 20
Congrats @chuhang1122 and team! A very solid step toward letting anyone create their own playable 3D worlds, with characters and dynamic interaction. This is a direction we’ve also been exploring in my own lab, so I’m especially happy about this progress. looking forward to
ViggleAI
@ViggleAI
Oct 19
Today we are releasing JST-2, the world's first full-stack physics-native world foundation model. Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D. Generate a 3D scene in seconds and expand it in real
Shenlong Wang
@ShenlongWang
Dec 2, 2025
We’re excited that from a single video we can now create a sim-ready 3D scene—objects are interactable, separated, complete, and physically stable. We also show how these indoor digital twins enable VFX, robot sim, and even 3D printing!
Hongchi Xia
@hongchix
Oct 8, 2025
#NeurIPS2025 We're excited to introduce <HoloScene>, which can create realistic and simulation-ready worlds from videos. It can recover every rigid-body object completeness, avoid geometry interpenetration, and maintain physical stability. Project page: xiahongchi.github.io/HoloScene/
1
Shenlong Wang
@ShenlongWang
Apr 4, 2025
Can we make images interactive with realistic physics? 🚀 Thrilled to share our #CVPR2025 work: PhysGen3D! From just a single image, PhysGen3D creates an interactive, physics-informed 3D scene, enabling us to explore and simulate realistic future scenarios interactively.
Boyuan Chen
@boyuanchen21
Apr 4, 2025
00:10
🚀 Introducing PhysGen3D – turn a single image into an interactive 3D world 🌍 From image ➡️ amodal 3D ➡️ physically grounded video You can control initial speed, mass, friction... and "imagine" what happens next 📄 Project page: by-luckk.github.io/PhysGen3D #3DVision #CVPR2025
1
Shenlong Wang
@ShenlongWang
Mar 25, 2025
Check out our new work, PhysTwin! It converts videos of deformable objects into real-time interactive demos with realistic physics. Highly recommend trying the demo out — it’s quite fun! 🚀 Led by the amazing @jiang_hanxiao.
Just Hanxiao
@jiang_hanxiao
Mar 25, 2025
🚀 How can we create interactive Physical Digital Twins from videos? Thrilled to share our latest work: PhysTwin! 🌟 Using inverse physics optimization, we generate photo-realistic, physically accurate, and real-time interactive virtual replicas. 🔥 🔗jianghanxiao.github.io/phystwin-web/
1
Shenlong Wang
@ShenlongWang
Mar 22, 2025
We are excited to present AutoVFX, an automatic video editing method delivering physics-accurate, fully controllable effects like pro VFX—yet as simple as a text prompt. @haoyuhsu88 and @ZhiHaoLin16 will showcase it at #3DV2025 in the coming week.
Hao-Yu (Max) Hsu
@haoyuhsu88
Mar 22, 2025
🎬Imagine creating professional visual effects (VFX) with just words! We introduce AutoVFX, a framework that creates physically realistic video effects directly from natural language instructions!