RectifiedHR：通過能量校正實現高效的高分辨率圖像生成

RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification

March 4, 2025

作者: Zhen Yang, Guibao Shen, Liang Hou, Mushui Liu, Luozhou Wang, Xin Tao, Pengfei Wan, Di Zhang, Ying-Cong Chen

cs.AI

摘要

擴散模型在各種圖像生成任務中取得了顯著進展。然而，當生成分辨率高於訓練期間使用的圖像時，其性能顯著下降。儘管存在多種生成高分辨率圖像的方法，但它們要么效率低下，要么受到複雜操作的阻礙。在本文中，我們提出了RectifiedHR，這是一種高效且簡單的無訓練高分辨率圖像生成解決方案。具體來說，我們引入了噪聲刷新策略，理論上只需幾行代碼即可解鎖模型的高分辨率生成能力並提高效率。此外，我們首次觀察到在高分辨率圖像生成過程中可能導致圖像模糊的能量衰減現象。為了解決這個問題，我們提出了一種能量校正策略，通過修改無分類器引導的超參數，有效提升了生成性能。我們的方法完全無需訓練，且實現邏輯簡單。通過與多種基線方法的廣泛比較，我們的RectifiedHR展示了卓越的效果和效率。

English

Diffusion models have achieved remarkable advances in various image generation tasks. However, their performance notably declines when generating images at resolutions higher than those used during the training period. Despite the existence of numerous methods for producing high-resolution images, they either suffer from inefficiency or are hindered by complex operations. In this paper, we propose RectifiedHR, an efficient and straightforward solution for training-free high-resolution image generation. Specifically, we introduce the noise refresh strategy, which theoretically only requires a few lines of code to unlock the model's high-resolution generation ability and improve efficiency. Additionally, we first observe the phenomenon of energy decay that may cause image blurriness during the high-resolution image generation process. To address this issue, we propose an Energy Rectification strategy, where modifying the hyperparameters of the classifier-free guidance effectively improves the generation performance. Our method is entirely training-free and boasts a simple implementation logic. Through extensive comparisons with numerous baseline methods, our RectifiedHR demonstrates superior effectiveness and efficiency.