TPA-Net: Generate A Dataset for Text to Physics-based Animation

TL;DR

This paper introduces TPA-Net, a dataset with high-resolution 3D physical simulations and textual descriptions to improve the physical realism of text-to-video generation systems.

Contribution

It presents an autonomous data generation method and a comprehensive dataset using advanced physical simulation techniques for better physical realism in text-to-video tasks.

Findings

Provides high-quality multi-view videos for T2V and NeRF research.

Uses state-of-the-art physical simulation methods like IPC and MPM.

Lays groundwork for fully automated text-to-video/simulation systems.

Abstract

Recent breakthroughs in Vision-Language (V&L) joint research have achieved remarkable results in various text-driven tasks. High-quality Text-to-video (T2V), a task that has been long considered mission-impossible, was proven feasible with reasonably good results in latest works. However, the resulting videos often have undesired artifacts largely because the system is purely data-driven and agnostic to the physical laws. To tackle this issue and further push T2V towards high-level physical realism, we present an autonomous data generation technique and a dataset, which intend to narrow the gap with a large number of multi-modal, 3D Text-to-Video/Simulation (T2V/S) data. In the dataset, we provide high-resolution 3D physical simulations for both solids and fluids, along with textual descriptions of the physical phenomena. We take advantage of state-of-the-art physical simulation methods (i) Incremental Potential Contact (IPC) and (ii) Material Point Method (MPM) to simulate diverse scenarios, including elastic deformations, material fractures, collisions, turbulence, etc. Additionally, high-quality, multi-view rendering videos are supplied for the benefit of T2V, Neural Radiance Fields (NeRF), and other communities. This work is the first step towards fully automated Text-to-Video/Simulation (T2V/S). Live examples and subsequent work are at https://sites.google.com/view/tpa-net.