DNF-SR：用于真实世界图像超分辨率的双输入与负感知特征微调
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
- Nankai University（南开大学）
- NKIARI, Shenzhen Futian（深圳福田NKIARI）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出DNF-SR，通过双输入拼接与负感知特征微调（NF2T），利用噪声多样性引导单步扩散模型，实现高保真且稳定的真实世界图像超分辨率。
AI中文摘要：
得益于扩散模型强大的生成先验，基于扩散的真实世界图像超分辨率（Real-ISR）方法已展现出令人瞩目的性能。为实现高效的Real-ISR，近期一些工作设计了单步扩散模型。然而，将低分辨率（LR）图像直接输入扩散模型会与其原始输入产生分布差距。缩小分布差距的一种直接方法是在LR潜在表示中添加噪声。然而，直接添加噪声不可避免地会破坏LR图像的内容。在本研究中，我们提出了DNF-SR，一种用于Real-ISR的双输入与负感知特征微调方法。首先，我们采用双输入策略，将原始LR图像与带噪LR输入拼接后输入基于扩散的图像编辑模型，从而确保高保真度的单步超分辨率，并提升感知与内容质量。其次，带噪LR输入中的噪声为输出引入了随机性和多样性。我们利用这一特性，提出了一种训练后优化方法——负感知特征微调（NF2T），引导模型生成更高质量的图像。NF2T将多个输出分为正负子集，并在图像空间和特征空间中定义隐式策略改进方向，从而进一步增强输出稳定性。大量实验表明，DNF-SR优于其他方法。代码将予以发布。
英文摘要：
Benefiting from the powerful generative priors of diffusion models, diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance.To achieve efficient Real-ISR, several recent works have designed one-step diffusion-based models.Howerver, unmediatedly feeding LR into a diffusion model creates a distributional gap with the model's original input.A straightforward approach to reduce the distribution gap is to introduce noise to the LR latents. However, directly adding noise inevitably corrupts the content of the LR images.In this study, we propose DNF-SR, a Dual-input and Negative-aware Feature fine-tuning method for Real-ISR.Specifically, we use a dual-input strategy that concatenates the original LR image with the noisy LR input and feeds them into a diffusion-based image editing model, ensuring both high-fidelity one-step super-resolution and improved perceptual and content consistency.Additionally, the noise present in the noisy LR input introduces randomness and diversity into the outputs. We exploit this property and propose a post-training optimization method, Negative-aware Feature Fine-Tuning (NF2T), which guides the model toward producing higher-quality results.NF^2T classifies multiple outputs into positive and negative subsets and then defines implicit policy improvement directions in both the image and feature spaces, thereby further enhancing the stability of the optimization.Extensive experiments show that DNF-SR outperforms other methods.Code will be released.
