PhotoQuilt: 通过引导式分块去噪实现无训练任意分辨率的光马赛克
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
AI总结：
提出PhotoQuilt框架，通过引导式分块去噪过程，在无需训练的情况下生成任意分辨率的光马赛克，兼顾全局结构与局部细节，并避免二次注意力成本。
摘要：
光马赛克是一种大图像，其局部区域被视为独立的瓦片，而整体排列形成连贯的场景。以高分辨率生成它们，使每个瓦片本身具有说服力，在计算上是昂贵的，因为画布必须同时容纳许多细节丰富的瓦片。我们提出了PhotoQuilt，一个无需训练的框架，可以生成任意分辨率的光马赛克。扩散模型难以同时满足两种尺度，因为直接高分辨率生成成本高昂，且倾向于生成一个平滑的图像而不是马赛克，而基于补丁的分块保留了局部细节但失去了全局结构。PhotoQuilt通过引导式分块去噪过程解决了这个问题。我们首先在低分辨率下生成全局构图以固定布局，然后在潜在空间中对其进行上采样并重新注入噪声以恢复生成能力。去噪在固定瓦片内进行，因此每个瓦片形成自己的图像，而共享的全局结构将它们保持在同一个布局中。由于瓦片生成是单独处理的，PhotoQuilt可以扩展到大型画布，而无需二次注意力成本。实验表明，PhotoQuilt在全局结构和局部真实性方面均优于当前基线。
英文摘要：
Photomosaics are large images whose local regions are seen as independent tiles while their overall arrangement forms a coherent scene. Generating them at high resolution, with every tile convincing in its own right, is computationally expensive, since the canvas must hold many detailed tiles at once. We present PhotoQuilt, a training-free framework that generates photomosaics at arbitrary resolution. Diffusion models struggle to satisfy both scales at once, as direct high-resolution generation is costly and tends toward one smooth image rather than a mosaic, while patch-based tiling keeps local detail but loses global structure. PhotoQuilt resolves this with a bootstrapped tiled denoising procedure. We first produce a global composition at low resolution to fix the layout, then upscale it in latent space and re-inject noise to restore generative capacity. Denoising proceeds within fixed tiles, so each forms its own image while the shared global structure holds them in one layout. Because tile generation is handled separately, PhotoQuilt scales to large canvases without quadratic attention cost. Experiments show that PhotoQuilt outperforms current baselines on both global structure and local realism.
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。
