发表机构
Tianjin University; The Hong Kong Polytechnic University（天津大学; 香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有循环视频生成质量差的问题，提出Loopy框架，通过锚定DiT的位置嵌入偏移策略，实现高质量、支持多格式及高级AIGC功能的循环视频生成，提升了时间一致性与视觉保真度。
AI 中文摘要
循环视频对于网页图形、游戏开发和社交媒体等实际应用至关重要。然而，现有方法通常无法生成高质量的循环视频，因为它们忽略了视频生成模型如何感知时间顺序及其与循环行为的关联。在本研究中，我们首次揭示了DiT（扩散Transformer）不同注意力层的位置嵌入表现出不同程度的位置控制，其中最显著的层充当锚点。我们将该锚定层定义为循环视频的参考点，为其余层提供强上下文先验，以促进生成连贯的视频内容。基于这一发现，我们提出了一种锚定位置嵌入偏移策略，根据各层的时间控制效应应用特定层的偏移长度，有效将DiT的时间感知从直线转变为圆形。利用该策略，我们开发了一个用于高质量循环视频生成的通用框架Loopy，支持RGB和RGBA视频，同时还能实现高级AIGC功能，如身份控制和风格迁移。实验表明，我们的方法显著提高了生成的循环视频的时间一致性和视觉保真度。发布的模型可在我们的网站获取：this https URL。
英文摘要
Looping videos are essential for practical applications such as web graphics, game development, and social media. However, existing approaches typically fail to generate high-quality looping videos due to the neglect of how video generation models perceive temporal order and how this relates to the looping behavior. In this work, we are the first to reveal that position embedding at different attention layers within DiT exhibits varying levels of positional control, with the most pronounced layer acting as an anchor. We formulate this anchored layer as the reference point of the looping video, offering strong contextual priors for the remaining layers to facilitate the generation of seamless and coherent video content. Based on this insight, we propose an anchored position embedding shifting strategy that applies layer-specific shift lengths according to each layer's temporal control effect, effectively transforming DiT's temporal perception from a straight line to a circle. Leveraging this strategy, we develop a general framework, Loopy, for high-quality looping video generation, supporting both RGB and RGBA videos, while also enabling advanced AIGC features such as identity control and style transfer. Experiments demonstrate that our approach significantly improves temporal consistency and visual fidelity in generated looping videos. The released model is available on our website: https://donghaotian123.github.io/Loopy.
Comments15 pages, 21 figures, accepted by ACM TOG
DOI：10.1145/3842544
