Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution

• URL: http://arxiv.org/abs/2509.14841v1
• Date: Thu, 18 Sep 2025 11:04:51 GMT
• Title: Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
• Authors: Hongjun Wang, Jiyuan Chen, Zhengwei Yin, Xuan Song, Yinqiang Zheng,
• Abstract summary: Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations.<n>We propose a targeted feature denoising framework, comprising noise detection and denoising modules.<n>Our framework demonstrates superior performance compared to previous regularization-based methods.
• Score: 40.723558636912784
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting degradations. Recently, numerous approaches such as Dropout and Feature Alignment have been proposed to suppress models' natural tendency to overfit degradations and yield promising results. Nevertheless, these works have assumed that models overfit to all degradation types (e.g., blur, noise, JPEG), while through careful investigations in this paper, we discover that models predominantly overfit to noise, largely attributable to its distinct degradation pattern compared to other degradation types. In this paper, we propose a targeted feature denoising framework, comprising noise detection and denoising modules. Our approach presents a general solution that can be seamlessly integrated with existing super-resolution models without requiring architectural modifications. Our framework demonstrates superior performance compared to previous regularization-based methods across five traditional benchmarks and datasets, encompassing both synthetic and real-world scenarios.

Related papers

• All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network [41.06285233763803]
  We propose Causal-deconfounding Wavelet-disentangled Prompt Network (CWP-Net) to perform effective AiOIR.<n>CWP-Net introduces two modules for decoupling, i.e., wavelet attention module of encoder and wavelet attention module of decoder.<n>Experiments on two all-in-one settings prove the effectiveness and superior performance of our proposed CWP-Net.
  arXiv  Detail & Related papers  (2026-03-04T08:43:11Z)
• Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion Models [10.74767402912109]
  We propose a zero-shot framework capable of handling various imaging inverse problems without model retraining.<n>We introduce a likelihood-guided noise refinement mechanism that derives a closed-form approximation of the likelihood score.<n>We integrate the Denoising Diffusion Implicit Models (DDIM) sampling strategy to further improve inference efficiency.
  arXiv  Detail & Related papers  (2025-06-16T11:56:50Z)
• Revealing the Implicit Noise-based Imprint of Generative Models [71.94916898756684]
  This paper presents a novel framework that leverages noise-based model-specific imprint for the detection task.<n>By aggregating imprints from various generative models, imprints of future models can be extrapolated to expand training data.<n>Our approach achieves state-of-the-art performance across three public benchmarks including GenImage, Synthbuster and Chameleon.
  arXiv  Detail & Related papers  (2025-03-12T12:04:53Z)
• Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding [67.57487747508179]
  Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model. In this paper, we propose a novel multiple-in-one IR model that can effectively restore images with both single and mixed degradations.
  arXiv  Detail & Related papers  (2024-11-25T09:26:34Z)
• Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness [4.339574774938128]
  We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models. Our framework allows users to customize the types of distortions to be optimally applied to images, which helps address the specific distortions relevant to their deployment.
  arXiv  Detail & Related papers  (2023-10-28T07:40:42Z)
• Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection [77.3530907443279]
  We propose a novel self-supervised framework to detect objects in degraded low resolution images. Our methods has achieved superior performance compared with existing methods when facing variant degradation situations.
  arXiv  Detail & Related papers  (2022-08-05T09:36:13Z)
• One Size Fits All: Hypernetwork for Tunable Image Restoration [5.33024001730262]
  We introduce a novel approach for tunable image restoration that achieves the accuracy of multiple models, each optimized for a different level of degradation. Our model can be optimized to restore as many degradation levels as required with a constant number of parameters and for various image restoration tasks.
  arXiv  Detail & Related papers  (2022-06-13T08:33:14Z)
• A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds [27.945034226654656]
  We propose a unified gated degradation model to generate a broad set of degradation cases using a random gate controller. Based on the degradation model, we propose simple baseline networks that can effectively handle non-blind, classical, practical degradation cases. Our empirical analysis shows that with the unified gated degradation model, the proposed baselines can achieve much better performance than existing methods.
  arXiv  Detail & Related papers  (2022-05-10T14:02:49Z)
• Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization [67.99082021804145]
  We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss) DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models.
  arXiv  Detail & Related papers  (2022-01-04T08:30:09Z)
• Kernel Adversarial Learning for Real-world Image Super-resolution [23.904933824966605]
  We propose a more realistic process to synthesise low-resolution images for real-world image SR by introducing a new Kernel Adversarial Learning Super-resolution framework. In the proposed framework, degradation kernels and noises are adaptively modelled rather than explicitly specified. We also propose a high-frequency selective objective and an iterative supervision process to further boost the model SR reconstruction accuracy.
  arXiv  Detail & Related papers  (2021-04-19T01:51:21Z)
• Designing a Practical Degradation Model for Deep Blind Image Super-Resolution [134.9023380383406]
  Single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. This paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations.
  arXiv  Detail & Related papers  (2021-03-25T17:40:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.