Pay Attention and Move Better: 利用注意力进行交互式运动生成与免训练编辑
Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing
AI总结：
针对运动扩散模型缺乏细粒度编辑能力的问题，提出基于注意力的MotionCLR模型，通过自注意力与交叉注意力实现交互式运动生成与免训练编辑，实验验证了其生成、编辑能力与可解释性。
摘要：
本研究深入探讨了人体运动生成的交互式编辑问题。以往的运动扩散模型缺乏对词级文本-运动对应关系的显式建模，且可解释性不佳，从而限制了其细粒度编辑能力。为解决这一问题，我们提出了一种基于注意力的运动扩散模型，即MotionCLR，通过CLeaR机制对注意力进行建模。技术上，MotionCLR分别利用自注意力和交叉注意力来建模模态内和跨模态的交互。具体而言，自注意力机制旨在衡量帧之间的序列相似性，并影响运动特征的顺序。相比之下，交叉注意力机制则用于寻找细粒度的词-序列对应关系，并激活运动序列中相应的时间步。基于这些关键特性，我们开发了一套多样且简单有效的运动编辑方法，通过操纵注意力图实现，例如运动（去）强调、原位运动替换以及基于示例的运动生成等。为进一步验证注意力机制的可解释性，我们还探索了通过注意力图进行动作计数和基于接地（grounded）运动生成的潜力。我们的实验结果表明，我们的方法具有良好的生成和编辑能力，且具备良好的可解释性。
英文摘要：
This research delves into the problem of interactive editing of human motion generation. Previous motion diffusion models lack explicit modeling of the word-level text-motion correspondence and good explainability, hence restricting their fine-grained editing ability. To address this issue, we propose an attention-based motion diffusion model, namely MotionCLR, with CLeaR modeling of attention mechanisms. Technically, MotionCLR models the in-modality and cross-modality interactions with self-attention and cross-attention, respectively. More specifically, the self-attention mechanism aims to measure the sequential similarity between frames and impacts the order of motion features. By contrast, the cross-attention mechanism works to find the fine-grained word-sequence correspondence and activate the corresponding timesteps in the motion sequence. Based on these key properties, we develop a versatile set of simple yet effective motion editing methods via manipulating attention maps, such as motion (de-)emphasizing, in-place motion replacement, and example-based motion generation, etc. For further verification of the explainability of the attention mechanism, we additionally explore the potential of action-counting and grounded motion generation ability via attention maps. Our experimental results show that our method enjoys good generation and editing ability with good explainability.
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。
