PhotoQuilt: 基于自举分块去噪的无训练任意分辨率照片拼贴图

摘要

马赛克图像由大量独立图块构成局部区域，其整体排列则形成连贯的场景。生成高分辨率马赛克图像时，若要每个图块自身具备说服力，计算成本极高——因为画布必须同时承载大量细节丰富的图块。为此，我们提出PhotoQuilt，一种无需训练的框架，能够生成任意分辨率的马赛克图像。扩散模型难以同时满足两种尺度需求：直接高分辨率生成成本高昂且倾向于生成平滑图像而非马赛克效果；而基于分块拼接的方法虽能保留局部细节，却会丧失全局结构。PhotoQuilt通过一种引导式分块去噪过程解决了这一问题：首先以低分辨率生成全局构图以确定布局，然后在潜空间中放大该构图并重新注入噪声以恢复生成能力。去噪过程在固定的图块内进行，使每个图块自成完整图像，同时共享的全局结构将它们统一在同一布局中。由于图块生成被独立处理，PhotoQuilt能够扩展至大型画布，而无需承担二次注意力开销。实验表明，PhotoQuilt在全局结构与局部真实性两方面均优于现有基线方法。

English

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.