潜在空间超分辨率：基于扩散模型的高分辨率图像生成

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models

March 24, 2025

作者: Jinho Jeong, Sangmin Han, Jinwoo Kim, Seon Joo Kim

cs.AI

摘要

本文提出了一种新颖的框架LSRNA，通过在潜在空间直接进行超分辨率处理，实现了更高分辨率（超过1K）的图像生成。现有的扩散模型在超越其训练分辨率时往往会出现结构失真或内容重复的问题。基于参考的方法通过上采样低分辨率参考图像来指导高分辨率生成，从而解决这些问题。然而，这些方法面临显著挑战：在潜在空间上采样通常会导致流形偏差，从而降低输出质量；而在RGB空间上采样则容易产生过度平滑的输出。为了克服这些限制，LSRNA结合了潜在空间超分辨率（LSR）以实现流形对齐，以及区域噪声添加（RNA）以增强高频细节。我们的大量实验表明，集成LSRNA在各种分辨率和指标上均优于最先进的基于参考的方法，同时揭示了潜在空间上采样在保持细节和锐度方面的关键作用。代码可在https://github.com/3587jjh/LSRNA获取。

English

In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling beyond their training resolutions, often leading to structural distortions or content repetition. Reference-based methods address the issues by upsampling a low-resolution reference to guide higher-resolution generation. However, they face significant challenges: upsampling in latent space often causes manifold deviation, which degrades output quality. On the other hand, upsampling in RGB space tends to produce overly smoothed outputs. To overcome these limitations, LSRNA combines Latent space Super-Resolution (LSR) for manifold alignment and Region-wise Noise Addition (RNA) to enhance high-frequency details. Our extensive experiments demonstrate that integrating LSRNA outperforms state-of-the-art reference-based methods across various resolutions and metrics, while showing the critical role of latent space upsampling in preserving detail and sharpness. The code is available at https://github.com/3587jjh/LSRNA.