通过结构引导生成更连贯的中间帧，提升动画过渡可控性。
StructInbet: Integrating Explicit Structural Guidance into Inbetween Frame Generation
- 引入显式结构引导，减少像素轨迹模糊性。
- 采用时序注意力机制，保持角色外观一致性。
- 适合需要精确控制动画过渡的创作者使用。
本文提出 StructInbet，一种基于显式结构引导的中间帧生成系统，以实现可控的动画过渡。该方法通过引入显式结构引导，有效降低了像素轨迹中的不确定性；同时采用时序注意力机制，融合前后关键帧的视觉身份信息，确保角色外观在生成过程中保持一致。该系统显著提升了生成结果的连贯性与可控性，适用于需要精确控制动画过渡的场景。
原文摘要 · Abstract (English)
In this paper, we propose StructInbet, an inbetweening system designed to generate controllable transitions over explicit structural guidance. StructInbet introduces two key contributions. First, we propose explicit structural guidance to the inbetweening problem to reduce the ambiguity inherent in pixel trajectories. Second, we adopt a temporal attention mechanism that incorporates visual identity from both the preceding and succeeding keyframes, ensuring consistency in character appearance.
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。