发表机构
Institute of Science Tokyo; Cygames, Inc.; The University of Tokyo（东京科学大学; Cygames 公司; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出运动风格滑块框架，通过端点监督在嵌入空间构建风格方向，实现无需中间真值的连续单调风格强度控制，兼容预训练扩散模型并支持异构数据集。
AI 中文摘要
现有的人体运动扩散方法提供了强大的运动生成质量，而近期的风格迁移模型能够注入目标风格线索，但对风格强度的细粒度连续控制仍未得到充分探索。在生产环境中，风格强度在艺术家和导演之间是主观的，因此实际需求并非一个通用的绝对单位，而是一条可靠的单调控制轴。我们提出了运动风格滑块（Motion Style Slider），一种用于端点监督连续控制的运动到运动风格迁移框架。给定一个内容运动和一个风格运动，我们在学习到的运动风格嵌入空间中构建一个风格方向，并用一个标量强度来条件化扩散生成。训练目标结合了扩散去噪与潜在强度正则化，以鼓励平滑且单调的风格缩放，而无需中间强度的真值运动。我们的框架与预训练的运动扩散骨干网络兼容，并支持异构风格数据集，包括多演员风格运动数据集。为测试超出范围的可使用性，我们还额外引入了一个小型真实捕捉的过度反应扩展，并针对这些未见目标评估大强度行为。实验衡量了可控性、插值/外推行为、内容保留和运动真实感，并对方向构建和损失设计进行了消融研究。
英文摘要
Existing human motion diffusion methods provide strong motion generation quality, and recent style transfer models can inject target style cues, but fine-grained continuous control of style intensity remains underexplored. In production, style intensity is subjective across artists and directors, so the practical requirement is not a universal absolute unit, but a reliable monotonic control axis. We propose Motion Style Slider, a motion-to-motion style transfer framework for endpoint-supervised continuous control. Given a content motion and a style motion, we construct a style direction in a learned motion-style embedding space and condition diffusion generation with a scalar intensity. The training objective combines diffusion denoising with latent intensity regularization to encourage smooth and monotonic style scaling without requiring intermediate-intensity ground-truth motions. Our framework is compatible with pretrained motion diffusion backbones and supports heterogeneous style datasets, including the multi-actor style motion dataset. To test out-of-range usability, we additionally introduce a small real-capture over-reaction extension and evaluate large-intensity behavior against these unseen targets. Experiments measure controllability, interpolation/extrapolation behavior, content preservation, and motion realism, with ablations on direction construction and loss design.
Journal refLiao, CC. et al. (2026). Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion. In ECCV 2026. Lecture Notes in Computer Science, vol 17026. Springer, Cham
DOI：10.1007/978-3-032-37595-7_7
