cs.CVNov 6, 2026

Improving the Diffusability of Motion Tokenizer

Authors: Guanhe Huang, Songqiao Han, Tangzheng Lian, Oya Celiktutan

Organizations: Department of Engineering, King’s College London, London, United Kingdom · Department of Mathematics, King’s College London, London, United Kingdom

Abstract

Latent diffusion models paired with a variational auto-encoder (VAE) tokenizer have shown promising performance for efficient text-driven human motion generation. However, motion latent diffusion suffers from a generation-reconstruction trade-off: simply increasing tokenizer capacity enhances reconstruction but fails to proportionally improve text-conditioned generation quality. We assume this trade-off stems from a spectral mismatch inside the VAE tokenizer: the encoder yields a latent space biased toward high frequencies, and the decoder introduces temporal artifacts. In this paper, we propose the Diffusable Motion Tokenizer (DiMoT) to improve the diffusability of the tokenizer, rather than scaling up the diffusion backbone. To improve text-conditioned optimization, Critic Spectral Adaptation (CSA) leverages a pretrained diffusion model as the critic to suppress high-frequency latent energy. To preserve motion dynamics, the Alpha-Flow Motion Decoder (AMD) performs generative decoding via average-velocity prediction, enabling efficient one-step decoding. Extensive experiments demonstrate that DiMoT achieves state-of-the-art performance across various challenging text-to-motion benchmarks, yielding superior motion fidelity and text-motion alignment. Project page: https://githubhgh.github.io/dimot/.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation

    Jan 21, 2026Yifei Liu, Changxing Ding, Ling Guo +2Diffusion Model GuidanceText-to-Motion Generation

  2. MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation

    Dec 15, 2025Yannan He, Garvita Tiwari, Xiaohan Zhang +4Latent Diffusion ModelsText-to-Motion Generation

  3. From Diffusion to Flow: Efficient Motion Generation in MotionGPT3

    Mar 23, 2026Jaymin Bhan, JiHong Jeon, SangYeop JeongText-to-Motion GenerationMotion Diffusion Models