MOGO：残差量化分层因果变换器用于高质量和实时3D人体运动生成
MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation
AI总结：
MOGO提出了一种高效的实时3D人体运动生成框架，通过MoSA-VQ和RQHC-Transformer实现高质量运动生成与实时响应，实验表明其在生成质量和实时性能上优于现有方法。
摘要：
近期基于变换器的文本到运动生成技术在合成高质量人类运动方面取得了显著进展。然而，同时实现高保真度、流式能力、实时响应性和可扩展性仍是一个根本挑战。本文提出MOGO（Motion Generation with One-pass），一种新的自回归框架，专门用于高效且实时的3D运动生成。MOGO包含两个关键组件：（1）MoSA-VQ，一种运动尺度自适应残差向量量化模块，通过可学习的缩放对运动序列进行层次离散化，生成紧凑且有表现力的表示；（2）RQHC-Transformer，一种残差量化分层因果变换器，能够在单次前向传递中生成多层运动标记，显著减少推理延迟。为了增强语义保真度，我们进一步引入了文本条件对齐机制，以提高在文本控制下的运动解码性能。在HumanML3D、KIT-ML和CMP等基准数据集上的广泛实验表明，MOGO在生成质量和实时性能、流式生成以及零样本设置下的泛化能力方面，与现有最先进的变换器方法相比，实现了竞争或优越的表现。
英文摘要：
Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Nevertheless, jointly achieving high fidelity, streaming capability, real-time responsiveness, and scalability remains a fundamental challenge. In this paper, we propose MOGO (Motion Generation with One-pass), a novel autoregressive framework tailored for efficient and real-time 3D motion generation. MOGO comprises two key components: (1) MoSA-VQ, a motion scale-adaptive residual vector quantization module that hierarchically discretizes motion sequences with learnable scaling to produce compact yet expressive representations; and (2) RQHC-Transformer, a residual quantized hierarchical causal transformer that generates multi-layer motion tokens in a single forward pass, significantly reducing inference latency. To enhance semantic fidelity, we further introduce a text condition alignment mechanism that improves motion decoding under textual control. Extensive experiments on benchmark datasets including HumanML3D, KIT-ML, and CMP demonstrate that MOGO achieves competitive or superior generation quality compared to state-of-the-art transformer-based methods, while offering substantial improvements in real-time performance, streaming generation, and generalization under zero-shot settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
