CVNov 26, 2024

PhysMotion: Physics-Grounded Dynamics From a Single Image

arXiv:2411.17189v232 citationsh-index: 15
Originality Incremental advance
AI Analysis

This addresses the challenge of realistic video generation for applications in computer vision and graphics, though it is incremental as it combines existing methods in a novel way.

The paper tackles the problem of generating physically plausible videos from a single image and input conditions by integrating physics-based simulations with generative models, resulting in high-quality, consistent motions validated through evaluations.

We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions (e.g., applied force and torque), producing high-quality, physically plausible video generation. By utilizing continuum mechanics-based simulations as a prior knowledge, our approach addresses the limitations of traditional data-driven generative models and result in more consistent physically plausible motions. Our framework begins by reconstructing a feed-forward 3D Gaussian from a single image through geometry optimization. This representation is then time-stepped using a differentiable Material Point Method (MPM) with continuum mechanics-based elastoplasticity models, which provides a strong foundation for realistic dynamics, albeit at a coarse level of detail. To enhance the geometry, appearance and ensure spatiotemporal consistency, we refine the initial simulation using a text-to-image (T2I) diffusion model with cross-frame attention, resulting in a physically plausible video that retains intricate details comparable to the input image. We conduct comprehensive qualitative and quantitative evaluations to validate the efficacy of our method. Our project page is available at: https://supertan0204.github.io/physmotion_website/.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes