CVMar 27, 2024

ParCo: Part-Coordinating Text-to-Motion Synthesis

arXiv:2403.18512v257 citationsh-index: 6Has CodeECCV
Originality Incremental advance
AI Analysis

It solves coordination problems in part-based motion synthesis for applications like animation and robotics, representing an incremental improvement over existing methods.

The paper tackles text-to-motion synthesis by addressing coordination issues in part-based methods, proposing ParCo to generate coordinated part motions with superior performance on benchmarks like HumanML3D and KIT-ML.

We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts. Moreover, introducing finer-grained part concepts poses computational complexity challenges. In this paper, we propose Part-Coordinating Text-to-Motion Synthesis (ParCo), endowed with enhanced capabilities for understanding part motions and communication among different part motion generators, ensuring a coordinated and fined-grained motion synthesis. Specifically, we discretize whole-body motion into multiple part motions to establish the prior concept of different parts. Afterward, we employ multiple lightweight generators designed to synthesize different part motions and coordinate them through our part coordination module. Our approach demonstrates superior performance on common benchmarks with economic computations, including HumanML3D and KIT-ML, providing substantial evidence of its effectiveness. Code is available at https://github.com/qrzou/ParCo .

Code Implementations1 repo
Foundations

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

Your Notes