PhotoQuilt: 透過引導式分塊去噪實現免訓練任意解析度照片馬賽克

摘要

拼接照片是一種大型影像，其局部區域被視為獨立拼塊，而整體排列則構成連貫的場景。以高解析度生成此類照片，並確保每個拼塊本身具備說服力，運算成本極高，因為畫布須同時容納大量細節豐富的拼塊。我們提出PhotoQuilt，這是一個無需訓練的框架，可生成任意解析度的拼接照片。擴散模型難以同時滿足兩種尺度：直接高解析度生成成本高昂，且傾向於產生單一平滑影像而非馬賽克；而基於區塊的拼接雖能保留局部細節，卻會失去整體結構。PhotoQuilt透過自舉式平鋪去噪程序解決此問題。我們先以低解析度生成全局構圖以確定佈局，接著在潛在空間中對其進行放大，並重新注入噪聲以恢復生成能力。去噪過程在固定的拼塊內進行，使每個拼塊形成自身影像，同時共享的全局結構將它們維持在同一佈局中。由於拼塊生成是獨立處理的，PhotoQuilt可擴展至大型畫布，且無需承受二次注意成本。實驗表明，PhotoQuilt在全局結構與局部真實感上均優於當前基準方法。

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.