What if we can take a few photos and turn it into an interactive physically realistic virtual world🌎? 📢Introducing AdaVoMP (ICML 26): generates volumetric physics fields at high spatial resolution making objects interactive and deformable🦾 🦣16^3x higher res (1024^3) ⚡️more accurate

3D assets usually have geometry and appearance like a Gaussian Splat you can capture📸, but not the physics needed for simulation To make them move realistically, we need physics fields throughout the volume. This requires generating the internals of the 3D assets too.

This continues on our VoMP (ICLR 26, line of work on fast accurate physics from any 3D object so they can be made interactive but: ⚡️higher resolution 🤖new learned adaptive structure 🗺️increase test time compute to increase generation resolution

We first introduce a new representation, SAV to encode input and generate over 🧱Large homogeneous regions can stay coarse. 🔬Only complex material boundaries and heterogeneous regions are recursively refined. 🎯So the model spends resolution where the physics actually changes.

2 new models: 1. Adaptive Geometry Transformer: encodes high-res 3D inputs from multi-view DINOv3 features🧊 2. Adaptive Material Generator: autoregressively generates a material tree from 1³ → 2³ → 4³ ... up to 1024³ by running the generator in a loop🌀 and it scales well📈

🤖Plug into robot evaluation frameworks! 🚀On hard test set (1024^3) we are over 25% and 30% more accurate on YM and density error than VoMP ⚡️at low-resolution (64^3) our structure uses only 9.14% of occupied voxels that VoMP operates over making our structure more efficient

📜 Paper: 🌐 Project Page: None of this would have been possible without the invaluable support from the team @DonglaiXiang @vm2358 @xuningy @gavrielstate @diwlevin @_shumash at @nvidia @NVIDIAAI @UofT @UofTCompSci And thanks to Gilles Daviet, Jean-Francois Lafleche, @BPerschall, Katherine Cheung, Ruchik Thaker, Andre Pradhana, @AnkaHeChen, Anita Hu, Charles Loop, @Caenorst, @frncswllms, @zhaohexu2001, Ken Museth