EPISODE · Mar 21, 2026 · 23 MIN
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
from Daily Paper Cast · host Jingwen Liang, Gengyu Wang
🤗 Upvotes: 34 | cs.CV Authors: Chenyang Gu, Mingyuan Zhang, Haozhe Xie, Zhongang Cai, Lei Yang, Ziwei Liu Title: Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer Arxiv: http://arxiv.org/abs/2603.19227v1 Abstract: Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a three-stage framework comprising condition feature extraction (Perception), discrete token generation (Planning), and diffusion-based motion synthesis (Control). Central to this framework is MoTok, a diffusion-based discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction by delegating motion recovery to a diffusion decoder, enabling compact single-layer tokens while preserving motion fidelity. For kinematic conditions, coarse constraints guide token generation during planning, while fine-grained constraints are enforced during control through diffusion-based optimization. This design prevents kinematic details from disrupting semantic token planning. On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens, reducing trajectory error from 0.72 cm to 0.08 cm and FID from 0.083 to 0.029. Unlike prior methods that degrade under stronger kinematic constraints, ours improves fidelity, reducing FID from 0.033 to 0.014.
What this episode covers
🤗 Upvotes: 34 | cs.CV Authors: Chenyang Gu, Mingyuan Zhang, Haozhe Xie, Zhongang Cai, Lei Yang, Ziwei Liu Title: Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer Arxiv: http://arxiv.org/abs/2603.19227v1 Abstract: Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a three-stage framework comprising condition feature extraction (Perception), discrete token generation (Planning), and diffusion-based motion synthesis (Control). Central to this framework is MoTok, a diffusion-based discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction by delegating motion recovery to a diffusion decoder, enabling compact single-layer tokens while preserving motion fidelity. For kinematic conditions, coarse constraints guide token generation during planning, while fine-grained constraints are enforced during control through diffusion-based optimization. This design prevents kinematic details from disrupting semantic token planning. On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens, reducing trajectory error from 0.72 cm to 0.08 cm and FID from 0.083 to 0.029. Unlike prior methods that degrade under stronger kinematic constraints, ours improves fidelity, reducing FID from 0.033 to 0.014.
NOW PLAYING
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
No transcript for this episode yet
Similar Episodes
No similar episodes found.