用隐式神经表示让扩散模型在少关键帧下生成更连贯真实的动作过渡。
Generative Motion In-betweening by Diffusion over Continuous Implicit Representations
- 基于隐式神经表示的扩散模型新框架，从稀疏关键帧中采样参数。
- 少关键帧场景下动作质量显著提升，保持关键帧准确与运动多样性。
- 适合需要高保真动作生成的动画、游戏开发场景。
生成模型在动作补间任务上取得了显著进展，能生成更复杂、多样且逼真的运动过渡。然而，现有方法在保留关键帧信息和确保运动连续性方面仍存在明显局限。本文提出一种基于动作隐式神经表示（INR）的新型流水线与采样优化策略，针对潜在扩散模型（LDM）。通过建立INR与潜在扩散空间中稀疏时空信息间的映射关系，模型可从极稀疏且模糊的关键帧数据中采样INR参数，并从流形中重建合理且平滑的动作。实验表明，该方法在关键帧数量极少的场景下显著提升了动作生成质量，同时保证了关键帧精度与补间动作的多样性。
原文摘要 · Abstract (English)
Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for more complex, varied, and realistic motion transitions. However, recent methods still exhibit noticeable limitations in preserving keyframe information and ensuring motion continuity. In this paper, we propose a novel pipeline and sampling optimization strategy for latent diffusion models (LDM) based on motion implicit neural representations (INR). By establishing a mapping between INR and sparse spatial or temporal information within latent diffusion, our model can sample the INR parameters from extremely sparse and ambiguous keyframe data and reconstruct plausible and smooth motions from the manifold. Our experiments demonstrate the superior performance of our model, which significantly improves motion generation quality in scenarios with few keyframes while ensuring both keyframe accuracy and diversity of in-between motions.
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。