用扩散模型反演实现任意步数超分辨率，单步即达顶尖效果。
Arbitrary-steps Image Super-resolution via Diffusion Inversion
- 通过部分噪声预测构建扩散过程中间态作为采样起点。
- 支持1到5步任意采样，单步即达当前最优性能。
- 适合追求高效超分的开发者与实际部署场景。
本文提出一种基于扩散反演的图像超分辨率技术，利用大规模预训练扩散模型中的丰富图像先验提升超分性能。设计了部分噪声预测策略，构建扩散模型的中间状态作为采样起始点。核心是深度噪声预测器，用于估计前向扩散过程中的最优噪声图。训练完成后，该预测器可沿扩散轨迹部分初始化采样过程，生成高质量高分辨率结果。相比现有方法，本方法具备灵活高效的采样机制，支持1至5步任意采样。即使仅用1步采样，性能也优于或媲美最新顶级方法。代码与模型已公开于 https://github.com/zsyOAOA/InvSR。
原文摘要 · Abstract (English)
This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point. Central to our approach is a deep noise predictor to estimate the optimal noise maps for the forward diffusion process. Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result. Compared to existing approaches, our method offers a flexible and efficient sampling mechanism that supports an arbitrary number of sampling steps, ranging from one to five. Even with a single sampling step, our method demonstrates superior or comparable performance to recent state-of-the-art approaches. The code and model are publicly available at https://github.com/zsyOAOA/InvSR.
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。