ReMoMask: Retrieval-Augmented Masked Motion Generation

TL;DR

ReMoMask is a novel framework that significantly improves text-to-motion generation by integrating retrieval-augmented methods, biomechanical constraints, and efficient diffusion models, achieving state-of-the-art results.

Contribution

It introduces a unified approach combining a bidirectional momentum model, semantic spatio-temporal attention, and classifier-free guidance for enhanced motion synthesis.

Findings

Achieves 3.88% and 10.97% lower FID scores on benchmarks.

Demonstrates improved diversity and physical plausibility.

Outperforms previous methods in standard evaluations.

Abstract

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models) suffer from limited diversity, error accumulation, and physical implausibility, while Retrieval-Augmented Generation (RAG) methods exhibit diffusion inertia, partial-mode collapse, and asynchronous artifacts. To address these limitations, we propose ReMoMask, a unified framework integrating three key innovations: 1) A Bidirectional Momentum Text-Motion Model decouples negative sample scale from batch size via momentum queues, substantially improving cross-modal retrieval precision; 2) A Semantic Spatio-temporal Attention mechanism enforces biomechanical constraints during part-level fusion to eliminate asynchronous artifacts; 3) RAG-Classier-Free Guidance incorporates minor unconditional generation to enhance generalization. Built upon MoMask's RVQ-VAE, ReMoMask efficiently generates temporally coherent motions in minimal steps. Extensive experiments on standard benchmarks demonstrate the state-of-the-art performance of ReMoMask, achieving a 3.88% and 10.97% improvement in FID scores on HumanML3D and KIT-ML, respectively, compared to the previous SOTA method RAG-T2M. Code: https://github.com/AIGeeksGroup/ReMoMask. Website: https://aigeeksgroup.github.io/ReMoMask.