ScrollScape: 通过视频扩散先验解锁32K图像生成
ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors
AI总结：
ScrollScape通过将超大比例图像生成转化为连续视频生成过程，利用视频模型的时序一致性确保结构完整性，实现32K分辨率的高质量图像生成。
摘要：
尽管扩散模型在生成传统尺寸图像方面表现优异，但将其扩展到极宽比（EAR）图像时常导致结构崩溃，如对象重复和空间碎片化。这种限制源于缺乏稳健的空间先验，因为静态文本到图像模型主要训练于传统尺寸图像分布。为克服这一瓶颈，我们提出了ScrollScape，一种新型框架，通过两个核心创新将EAR图像生成转化为连续视频生成过程。通过将大规模画布的空间扩展映射到视频帧的时序演变，ScrollScape利用视频模型的内在时序一致性作为强大的全局约束，确保长距离结构完整性。具体而言，扫描位置编码（ScanPE）将全局坐标分布到帧上，作为灵活的移动摄像机；滚动超分辨率（ScrollSR）利用视频超分辨率先验来规避内存瓶颈，高效地将输出扩展到前所未有的32K分辨率。在经过精心编纂的3K多比例图像数据集上微调后，ScrollScape有效对齐了预训练的视频先验与EAR生成任务。广泛评估表明，它显著优于现有图像扩散基线，消除了严重的局部化伪影。因此，我们的方法克服了固有的结构瓶颈，确保在极端尺度下不同领域中的卓越全局一致性和视觉保真度。
英文摘要：
While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often triggers catastrophic structural failures, such as object repetition and spatial fragmentation. This limitation fundamentally stems from a lack of robust spatial priors, as static text-to-image models are primarily trained on image distributions with conventional dimensions. To overcome this bottleneck, we present ScrollScape, a novel framework that reformulates EAR image synthesis into a continuous video generation process through two core innovations. By mapping the spatial expansion of a massive canvas to the temporal evolution of video frames, ScrollScape leverages the inherent temporal consistency of video models as a powerful global constraint to ensure long-range structural integrity. Specifically, Scanning Positional Encoding (ScanPE) distributes global coordinates across frames to act as a flexible moving camera, while Scrolling Super-Resolution (ScrollSR) leverages video super-resolution priors to circumvent memory bottlenecks, efficiently scaling outputs to an unprecedented 32K resolution. Fine-tuned on a curated 3K multi-ratio image dataset, ScrollScape effectively aligns pre-trained video priors with the EAR generation task. Extensive evaluations demonstrate that it significantly outperforms existing image-diffusion baselines by eliminating severe localized artifacts. Consequently, our method overcomes inherent structural bottlenecks to ensure exceptional global coherence and visual fidelity across diverse domains at extreme scales.
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。
