DNF-SR：面向真实世界图像超分辨率的双输入与负样本感知特征微调
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
把预训练扩散图像编辑模型当作单步 Real-ISR 的生成先验，用「原始 LR + 加噪 LR」双输入拼接来同时保住保真度与感知质量，并用正/负样本分组的后训练偏好优化（NF²T）在图像与特征空间定义隐式策略改进方向——这套「负样本感知微调」思路可直接迁移到其他一步扩散复原/编辑任务的输出筛选与对齐上。
原文依据 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
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论得益于扩散模型强大的生成先验，基于扩散模型的真实世界图像超分辨率（Real-ISR）方法已展现出令人印象深刻的性能。为实现高效的 Real-ISR，近期若干工作设计了基于扩散模型的单步模型。然而，将低分辨率（LR）图像不加处理地直接送入扩散模型，会与模型原本的输入之间产生分布差距。缩小该分布差距的一种直接做法是向 LR 潜变量引入噪声，但直接加噪不可避免地会破坏 LR 图像的内容。本研究提出 DNF-SR，一种面向 Real-ISR 的双输入与负样本感知特征微调方法。具体而言，我们采用双输入策略，将原始 LR 图像与加噪 LR 输入拼接后送入基于扩散模型的图像编辑模型，从而在保证高保真单步超分辨率的同时改善感知一致性与内容一致性。此外，加噪 LR 输入中的噪声为输出引入了随机性与多样性。我们利用这一特性，提出一种后训练优化方法——负样本感知特征微调（NF²T），引导模型产生更高质量的结果。NF²T 将多个输出划分为正样本子集与负样本子集，随后在图像空间与特征空间中定义隐式的策略改进方向，从而进一步增强优化的稳定性。大量实验表明，DNF-SR 优于其他方法。代码将公开。
英文原文摘要 1545 字符
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.