SmoothSync: Dual-Stream Diffusion Transformers for Jitter-Robust Beat-Synchronized Gesture Generation from Quantized Audio

TL;DR

SmoothSync introduces a dual-stream diffusion transformer framework utilizing quantized audio tokens to generate synchronized, smooth, and diverse co-speech gestures, effectively reducing jitter and foot sliding issues.

Contribution

The paper proposes a novel dual-stream diffusion transformer architecture with jitter-suppression and probabilistic quantization for improved gesture synchronization and diversity.

Findings

Outperforms state-of-the-art by -30.6% FGD on BEAT2

Reduces jitter and foot sliding by over 60%

Enhances gesture diversity by 8.4%

Abstract

Co-speech gesture generation is a critical area of research aimed at synthesizing speech-synchronized human-like gestures. Existing methods often suffer from issues such as rhythmic inconsistency, motion jitter, foot sliding and limited multi-sampling diversity. In this paper, we present SmoothSync, a novel framework that leverages quantized audio tokens in a novel dual-stream Diffusion Transformer (DiT) architecture to synthesis holistic gestures and enhance sampling variation. Specifically, we (1) fuse audio-motion features via complementary transformer streams to achieve superior synchronization, (2) introduce a jitter-suppression loss to improve temporal smoothness, (3) implement probabilistic audio quantization to generate distinct gesture sequences from identical inputs. To reliably evaluate beat synchronization under jitter, we introduce Smooth-BC, a robust variant of the beat consistency metric less sensitive to motion noise. Comprehensive experiments on the BEAT2 and SHOW datasets demonstrate SmoothSync's superiority, outperforming state-of-the-art methods by -30.6% FGD, 10.3% Smooth-BC, and 8.4% Diversity on BEAT2, while reducing jitter and foot sliding by -62.9% and -17.1% respectively. The code will be released to facilitate future research.