Tutorials
Coordinate-Based Dual-Constrained Autoregressive Motion Generation
arXiv:2604.08088v1 Announce Type: new Abstract: Text-to-motion generation has attracted increasing attention in the research community recently, with potential applications in animation, virtual reali
arXiv:2604.08088v1 Announce Type: new Abstract: Text-to-motion generation has attracted increasing attention in the research community recently, with potential applications in animation, virtual reality, robotics, and human-computer interaction. Diffusion and autoregressive models are two popular and parallel research directions for text-to-motion generation. However, diffusion models often suffer from error amplification during noise prediction, while autoregressive models exhibit mode collapse due to motion discretization. To address these limitations, we propose a flexible, high-fidelity, and semantically faithful text-to-motion framework, named Coordinate-based Dual-constrained Autoregressive Motion Generation (CDAMD). With motion coordinates as input, CDAMD follows the autoregressive paradigm and leverages diffusion-inspired multi-layer perceptrons to enhance the fidelity of predicted motions. Furthermore, a Dual-Constrained Causal Mask is introduced to guide autoregressive generation, where motion tokens act as priors and are concatenated with textual encodings. Since there is limited work on coordinate-based motion synthesis, we establish new benchmarks for both text-to-motion generation and motion editing. Experimental results demonstrate that our approach achieves state-of-the-art performance in terms of both fidelity and semantic consistency on these benchmarks.
Related
- Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
- Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
- Analyzing Multimodal Interaction Strategies for LLM-Assisted Manipulation of 3D Scenes
- MoRight: Motion Control Done Right
Source: arXiv cs.CV | 2026-04-10