The emergence of 3D Gaussian splatting (3DGS) has greatly accelerated rendering in novel
view synthesis. Unlike neural implicit representations like neural radiance fields (NeRFs) …

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 …

Efficient acquisition of real-world embodied data has been increasingly critical. However,
large-scale demonstrations captured by remote operation tend to take extremely high costs …

This paper studies the problem of estimating physical properties (system identification)
through visual observations. To facilitate geometry-aware guidance in physical property …

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 …

Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by
enabling machines to create and interpret visual data with unprecedented sophistication …

We introduce PhysMotion, a novel framework that leverages principled physics-based
simulations to guide intermediate 3D representations generated from a single image 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 present a computational framework that transforms single images into 3D physical
objects. The visual geometry of a physical object in an image is determined by three …

Recent advancements in 3D generation models have opened new possibilities for
simulating dynamic 3D object movements and customizing behaviors, yet creating this …