用修正流解码离散动作令牌，生成更自然的连续动作
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
- 将离散令牌解码为连续动作，通过条件生成保证流畅性
- 在HumanML3D上达FID 0.032，KIT-ML上为0.169，性能领先
- 兼容任意离散框架，适合追求真实动作生成的研究者
人体动作本质上是连续且动态的，给生成模型带来挑战。尽管离散生成方法广泛应用，但存在表达能力有限和帧级噪声问题；而连续方法虽更平滑自然，却常因高维复杂性和数据不足难以遵循条件信号。为解决离散与连续表示间的“不协调”问题，我们提出DisCoRD：通过修正流解码将离散动作令牌映射到连续原始动作空间。核心思想是将令牌解码视为条件生成任务，确保捕捉细微动态，实现更平滑自然的动作生成。该方法兼容任何基于离散的框架，在多种设置下提升自然度而不牺牲条件忠实性。大量实验表明，DisCoRD在HumanML3D上达到FID 0.032，KIT-ML上为0.169，确立了其在连接离散效率与连续真实之间的强大能力。
原文摘要 · Abstract (English)
Human motion is inherently continuous and dynamic, posing significant challenges for generative models. While discrete generation methods are widely used, they suffer from limited expressiveness and frame-wise noise artifacts. In contrast, continuous approaches produce smoother, more natural motion but often struggle to adhere to conditioning signals due to high-dimensional complexity and limited training data. To resolve this 'discord' between discrete and continuous representations we introduce DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding, a novel method that leverages rectified flow to decode discrete motion tokens in the continuous, raw motion space. Our core idea is to frame token decoding as a conditional generation task, ensuring that DisCoRD captures fine-grained dynamics and achieves smoother, more natural motions. Compatible with any discrete-based framework, our method enhances naturalness without compromising faithfulness to the conditioning signals on diverse settings. Extensive evaluations demonstrate that DisCoRD achieves state-of-the-art performance, with FID of 0.032 on HumanML3D and 0.169 on KIT-ML. These results establish DisCoRD as a robust solution for bridging the divide between discrete efficiency and continuous realism. Project website: https://whwjdqls.github.io/discord-motion/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。