人体运动合成:一种用于运动拼接与中间帧生成的扩散方法
Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening
AI总结:
针对现有运动拼接与中间帧生成方法需人工介入或难处理长序列的问题,提出带Transformer去噪器的扩散模型,可生成5秒75帧的平滑逼真运动,经定量与视觉评估性能优异。
摘要:
人体运动生成是诸多领域的重要研究方向。本研究针对运动拼接与中间帧生成问题展开,现有方法要么需要人工投入,要么无法处理较长序列。为应对这些挑战,我们提出一种带有基于Transformer的去噪器的扩散模型,用于生成逼真的人体运动。该方法在生成中间帧序列方面表现优异,可将数量可变的输入姿态转换为平滑逼真的运动序列,序列包含75帧,帧率为15fps,总时长为5秒。我们采用Frechet Inception Distance (FID)、多样性、多模态性等定量指标,并结合生成结果的视觉评估,对方法性能进行了验证。
英文摘要:
Human motion generation is an important area of research in many fields. In this work, we tackle the problem of motion stitching and in-betweening. Current methods either require manual efforts, or are incapable of handling longer sequences. To address these challenges, we propose a diffusion model with a transformer-based denoiser to generate realistic human motion. Our method demonstrated strong performance in generating in-betweening sequences, transforming a variable number of input poses into smooth and realistic motion sequences consisting of 75 frames at 15 fps, resulting in a total duration of 5 seconds. We present the performance evaluation of our method using quantitative metrics such as Frechet Inception Distance (FID), Diversity, and Multimodality, along with visual assessments of the generated outputs.
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。