深度组合相位扩散用于长运动序列生成
Deep Compositional Phase Diffusion for Long Motion Sequence Generation
AI总结：
针对多语义运动片段组合生成中的过渡不连续问题，提出组合相位扩散框架，利用SPDM和TPDM在潜在频域整合语义与相位信息，实现语义对齐且过渡连续的长运动序列生成，并支持运动插值。
摘要：
近期关于运动生成的研究在生成具有单一语义对齐的运动方面取得了显著进展。然而，当使用这些模型来创建包含多个语义生成运动片段的组合序列时，它们往往难以在片段之间的过渡边界处保持运动动态的连续性，导致尴尬的过渡和突兀的伪影。为了解决这些挑战，我们提出了组合相位扩散（Compositional Phase Diffusion），它利用语义相位扩散模块（SPDM）和过渡相位扩散模块（TPDM）在扩散过程中逐步整合来自相邻运动片段的语义引导和相位细节。具体而言，SPDM和TPDM在由预训练的动作中心运动相位自编码器（ACT-PAE）建立的潜在运动频域内运行。这使得它们能够在训练期间从可变长度的运动片段中学习语义重要且过渡感知的相位信息。实验结果表明，我们提出的框架在生成与输入条件语义对齐的组合运动序列方面表现出竞争性能，同时保持了前后运动片段之间的相位过渡连续性。此外，通过在扩散过程中保持输入运动序列的相位参数固定，实现了运动插值（motion inbetweening）任务，展示了将所提出框架扩展到各种应用场景的潜力。代码可在 https://github.com/asdryau/TransPhase 获取。
英文摘要：
Recent research on motion generation has shown significant progress in generating semantically aligned motion with singular semantics. However, when employing these models to create composite sequences containing multiple semantically generated motion clips, they often struggle to preserve the continuity of motion dynamics at the transition boundaries between clips, resulting in awkward transitions and abrupt artifacts. To address these challenges, we present Compositional Phase Diffusion, which leverages the Semantic Phase Diffusion Module (SPDM) and Transitional Phase Diffusion Module (TPDM) to progressively incorporate semantic guidance and phase details from adjacent motion clips into the diffusion process. Specifically, SPDM and TPDM operate within the latent motion frequency domain established by the pre-trained Action-Centric Motion Phase Autoencoder (ACT-PAE). This allows them to learn semantically important and transition-aware phase information from variable-length motion clips during training. Experimental results demonstrate the competitive performance of our proposed framework in generating compositional motion sequences that align semantically with the input conditions, while preserving phase transitional continuity between preceding and succeeding motion clips. Additionally, motion inbetweening task is made possible by keeping the phase parameter of the input motion sequences fixed throughout the diffusion process, showcasing the potential for extending the proposed framework to accommodate various application scenarios. Codes are available at https://github.com/asdryau/TransPhase.
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。
