在潜在空间做超分，让扩散模型生成超过1K分辨率的清晰图像。
Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models
- 在潜在空间进行超分辨率，保持特征流形对齐
- 结合区域噪声添加，显著提升高频细节
- 适合需要高分辨率图像生成的研究者
本文提出LSRNA框架，通过在潜在空间直接进行超分辨率，实现超过1K分辨率的图像生成。现有扩散模型在扩展分辨率时常出现结构失真或内容重复问题。参考方法虽可引导生成，但潜在空间上采样易引发流形偏离，导致质量下降；而RGB空间上采样则使输出过度平滑。LSRNA融合潜在空间超分辨率（LSR）以保持流形对齐，并引入区域噪声添加（RNA）增强高频细节。大量实验表明，集成LSRNA优于当前最优的参考式方法，在多种分辨率与评估指标下表现更佳，凸显了潜在空间上采样在保留细节与锐度中的关键作用。代码已开源：https://github.com/3587jjh/LSRNA。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。