Diffusion-based Human Motion Style Transfer with Semantic Guidance

TL;DR

This paper introduces a diffusion-based two-stage framework for few-shot 3D human motion style transfer that effectively handles unseen styles with minimal data, outperforming existing methods.

Contribution

It proposes a novel diffusion model approach with semantic guidance for few-shot motion style transfer, addressing limitations of previous AdaIN-based methods.

Findings

Achieves state-of-the-art style transfer quality.

Effective with only a single style example.

Demonstrates practical applicability in animation.

Abstract

3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN- based methods necessitate datasets with balanced style distribution and content/style labels to train the clustered latent space. However, we may encounter a single unseen style example in practical scenarios, but not in sufficient quantity to constitute a style cluster for AdaIN-based methods. Therefore, in this paper, we propose a novel two-stage framework for few-shot style transfer learning based on the diffusion model. Specifically, in the first stage, we pre-train a diffusion-based text-to-motion model as a generative prior so that it can cope with various content motion inputs. In the second stage, based on the single style example, we fine-tune the pre-trained diffusion model in a few-shot manner to make it capable of style transfer. The key idea is regarding the reverse process of diffusion as a motion-style translation process since the motion styles can be viewed as special motion variations. During the fine-tuning for style transfer, a simple yet effective semantic-guided style transfer loss coordinated with style example reconstruction loss is introduced to supervise the style transfer in CLIP semantic space. The qualitative and quantitative evaluations demonstrate that our method can achieve state-of-the-art performance and has practical applications.