DC-Motion: Decoupling Semantics and Details via Discrete-Continuous Tokens for Human Motion Generation

• URL: http://arxiv.org/abs/2606.14721v1
• Date: Thu, 28 May 2026 11:47:11 GMT
• Title: DC-Motion: Decoupling Semantics and Details via Discrete-Continuous Tokens for Human Motion Generation
• Abstract summary: We introduce DC-Motion, a factorized generative framework designed to explicitly decouple semantics and details via discrete-continuous tokens.<n>A masked AR model predicts the discrete structure from text, and a lightweight residual diffusion model recovers the continuous physical details.<n>On both HumanML3D and KIT-ML datasets, DC-Motion achieves state-of-the-art performance, delivering the best FID for motion realism and R-precision for text alignment.
• Score: 11.57444637723047
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-motion generation requires synthesizing physically realistic dynamics that strictly follow complex and long-horizon textual instructions. Existing approaches rely on homogeneous representation spaces that may fail to capture the hierarchical nature of human motion, with diffusion models struggling at compositional semantic reasoning and AR models sacrificing fine-grained physical details due to quantization. To solve it, we introduce DC-Motion, a factorized generative framework designed to explicitly decouple semantics and details via discrete-continuous tokens. A Discrete-Continuous VAE (DC-VAE) first decomposes motion into discrete tokens for semantics and continuous residuals for fine-grained dynamics. Then, a masked AR model predicts the discrete structure from text, and a lightweight residual diffusion model recovers the continuous physical details. Extensive experiments demonstrate that DC-Motion effectively improves the capability to follow complex instructions. By effectively balancing semantic controllability and physical realism, our approach offers a highly adaptable modeling paradigm for human motion generation. On both HumanML3D and KIT-ML datasets, DC-Motion achieves state-of-the-art performance, delivering the best FID for motion realism and R-precision for text alignment.

Related papers

• Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation [19.887078319028102]
  We propose a unifiedtemporal decoupled framework named DeMoDiff to redesign motion representation and architecture.<n>Our framework achieves state-of-the-art reconstruction performance and compelling motion generation results.
  arXiv  Detail & Related papers  (2026-08-24T14:04:35Z)
• Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling [32.83313595986613]
  We propose a framework for expanding the motion representation space by leveraging large-scale synthetic human motion.<n>Unlike conventional tokenizers trained on narrow data distributions, our approach jointly scales both the training distribution and the discrete codebook.<n>We demonstrate that training with synthetic motion substantially improves the coverage and compositionality of the learned motion vocabulary.
  arXiv  Detail & Related papers  (2026-06-25T20:50:31Z)
• In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics [109.99871326497333]
  In-Context Model Predictive Generation (ICMPG) is a framework that integrates language-model planning with inference-time physical feedback.<n>ICMPG reformulates motion synthesis as a Model Predictive Control (MPC)-like process with two modules.
  arXiv  Detail & Related papers  (2026-06-25T12:50:33Z)
• Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion [60.186310080523135]
  Bifurcation of generative modeling into autoregressive approaches for discrete data (text) and diffusion approaches for continuous data (images) hinders development of truly unified multimodal systems.<n>We propose textbfCoM-DAD, a novel probabilistic framework that reformulates multimodal generation as a hierarchical dual-process.<n>Our method demonstrates superior stability over standard masked modeling, establishing a new paradigm for scalable, unified text-image generation.
  arXiv  Detail & Related papers  (2026-01-07T16:21:19Z)
• MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing [53.98607267063729]
  MotionVerse is a framework to comprehend, generate, and edit human motion in both single-person and multi-person scenarios.<n>We employ a motion tokenizer with residual quantization, which converts continuous motion sequences into multi-stream discrete tokens.<n>We also introduce a textitDelay Parallel Modeling strategy, which temporally staggers the encoding of residual token streams.
  arXiv  Detail & Related papers  (2025-09-28T04:20:56Z)
• Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation [31.484189825477877]
  Motion-R1 is a unified motion-language modeling framework that integrates a Chain-of-Thought mechanism.<n>By explicitly decomposing complex textual instructions into logically structured action paths, Motion-R1 provides high-level semantic guidance for motion generation.<n>Experiments across multiple benchmark datasets demonstrate that Motion-R1 achieves competitive or superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-12T05:21:43Z)
• Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion [33.9786226622757]
  We propose a robust motion generation framework MoMADiff to generate 3D human motion from text descriptions.<n>Our model supports flexible user-provided specification, enabling precise control over both spatial and temporal aspects of motion synthesis.<n>Our method consistently outperforms state-of-the-art models in motion quality, instruction fidelity, and adherence.
  arXiv  Detail & Related papers  (2025-05-16T09:06:15Z)
• Text-driven Human Motion Generation with Motion Masked Diffusion Model [23.637853270123045]
  Text human motion generation is a task that synthesizes human motion sequences conditioned on natural language. Current diffusion model-based approaches have outstanding performance in the diversity and multimodality of generation. We propose Motion Masked Diffusion Model bftext(MMDM), a novel human motion mechanism for diffusion model.
  arXiv  Detail & Related papers  (2024-09-29T12:26:24Z)
• Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model [60.27825196999742]
  We propose a novel Basic-to-Advanced Hierarchical Diffusion Model, named B2A-HDM, to collaboratively exploit low-dimensional and high-dimensional diffusion models for detailed motion synthesis. Specifically, the basic diffusion model in low-dimensional latent space provides the intermediate denoising result that is consistent with the textual description. The advanced diffusion model in high-dimensional latent space focuses on the following detail-enhancing denoising process.
  arXiv  Detail & Related papers  (2023-12-18T06:30:39Z)
• SemanticBoost: Elevating Motion Generation with Augmented Textual Cues [73.83255805408126]
  Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD) The CAMD approach provides an all-encompassing solution for generating high-quality, semantically consistent motion sequences. Our experimental results demonstrate that SemanticBoost, as a diffusion-based method, outperforms auto-regressive-based techniques.
  arXiv  Detail & Related papers  (2023-10-31T09:58:11Z)
• Priority-Centric Human Motion Generation in Discrete Latent Space [59.401128190423535]
  We introduce a Priority-Centric Motion Discrete Diffusion Model (M2DM) for text-to-motion generation. M2DM incorporates a global self-attention mechanism and a regularization term to counteract code collapse. We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token.
  arXiv  Detail & Related papers  (2023-08-28T10:40:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.