Open Access

ARTICLE

Motion In-Betweening via Frequency-Domain Diffusion Model

Qiang Zhang¹, Shuo Feng¹, Shanxiong Chen², Teng Wan¹, Ying Qi^1,*

1 Department of Computer Science and Engineering, Northwest Normal University, Lanzhou, 730070, China
2 Department of Computer and Information Science, Southwest University, Chongqing, 400715, China

* Corresponding Author: Ying Qi. Email:

Computers, Materials & Continua 2026, 86(1), 1-22. https://doi.org/10.32604/cmc.2025.068247

Received 23 May 2025; Accepted 17 July 2025; Issue published 10 November 2025

Abstract

Human motion modeling is a core technology in computer animation, game development, and human-computer interaction. In particular, generating natural and coherent in-between motion using only the initial and terminal frames remains a fundamental yet unresolved challenge. Existing methods typically rely on dense keyframe inputs or complex prior structures, making it difficult to balance motion quality and plausibility under conditions such as sparse constraints, long-term dependencies, and diverse motion styles. To address this, we propose a motion generation framework based on a frequency-domain diffusion model, which aims to better model complex motion distributions and enhance generation stability under sparse conditions. Our method maps motion sequences to the frequency domain via the Discrete Cosine Transform (DCT), enabling more effective modeling of low-frequency motion structures while suppressing high-frequency noise. A denoising network based on self-attention is introduced to capture long-range temporal dependencies and improve global structural awareness. Additionally, a multi-objective loss function is employed to jointly optimize motion smoothness, pose diversity, and anatomical consistency, enhancing the realism and physical plausibility of the generated sequences. Comparative experiments on the Human3.6M and LaFAN1 datasets demonstrate that our method outperforms state-of-the-art approaches across multiple performance metrics, showing stronger capabilities in generating intermediate motion frames. This research offers a new perspective and methodology for human motion generation and holds promise for applications in character animation, game development, and virtual interaction.

---

Keywords

---