Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation

TL;DR

This paper introduces a hierarchical deformation model and a physics-aware correction scheme to generate diverse, high-fidelity, and physically valid articulated meshes from limited examples, advancing few-shot mesh generation.

Contribution

The paper proposes a novel hierarchical deformation-based generative model and a physics-aware correction method for few-shot articulated mesh generation, improving diversity, fidelity, and physical validity.

Findings

Outperforms previous methods in diversity and visual fidelity

Achieves higher physical validity in generated meshes

Validated through extensive experiments on 6 categories

Abstract

We study the problem of few-shot physically-aware articulated mesh generation. By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity. Previous mesh generative models either have difficulties in depicting a diverse data space from only a few examples or fail to ensure physical validity of their samples. Regarding the above challenges, we propose two key innovations, including 1) a hierarchical mesh deformation-based generative model based upon the divide-and-conquer philosophy to alleviate the few-shot challenge by borrowing transferrable deformation patterns from large scale rigid meshes and 2) a physics-aware deformation correction scheme to encourage physically plausible generations. We conduct extensive experiments on 6 articulated categories to demonstrate the superiority of our method in generating articulated meshes with better diversity, higher visual fidelity, and better physical validity over previous methods in the few-shot setting. Further, we validate solid contributions of our two innovations in the ablation study. Project page with code is available at https://meowuu7.github.io/few-arti-obj-gen.