We introduce PhysGaussian a new method that seamlessly integrates physically grounded
Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis …

Dynamic 3D interaction has been attracting a lot of attention recently. However, creating
such 4D content remains challenging. One solution is to animate 3D scenes with physics …

While humans effortlessly discern intrinsic dynamics and adapt to new scenarios, modern AI
systems often struggle. Current methods for visual grounding of dynamics either use pure …

Reduced-order simulation is an emerging method for accelerating physical simulations with
high DOFs, and recently developed neural-network-based methods with nonlinear …

The idea of using a neural network to represent continuous vector fields (ie, neural fields)
has become popular for solving PDEs arising from physics simulations. Here, the classical …

Neural Fields have emerged as a transformative approach for 3D scene representation in
computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and …

While humans effortlessly discern intrinsic dynamics and adapt to new scenarios, modern AI
systems often struggle. Current methods for visual grounding of dynamics either use pure …

We introduce PhysMotion, a novel framework that leverages principled physics-based
simulations to guide intermediate 3D representations generated from a single image and …

Recently, significant advancements have been made in the reconstruction and generation of
3D assets, including static cases and those with physical interactions. To recover the …

We present a neural network-based simulation super-resolution framework that can
efficiently and realistically enhance a facial performance produced by a low-cost, real-time …