Exploiting Self-Supervised Constraints in Image Super-Resolution

• URL: http://arxiv.org/abs/2404.00260v1
• Date: Sat, 30 Mar 2024 06:18:50 GMT
• Title: Exploiting Self-Supervised Constraints in Image Super-Resolution
• Authors: Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu,
• Abstract summary: This paper introduces a novel self-supervised constraint for single image super-resolution, termed SSC-SR. SSC-SR uniquely addresses the divergence in image complexity by employing a dual asymmetric paradigm and a target model updated via exponential moving average to enhance stability. Empirical evaluations reveal that our SSC-SR framework delivers substantial enhancements on a variety of benchmark datasets, achieving an average increase of 0.1 dB over EDSR and 0.06 dB over SwinIR.
• Score: 72.35265021054471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for single image super-resolution, termed SSC-SR. SSC-SR uniquely addresses the divergence in image complexity by employing a dual asymmetric paradigm and a target model updated via exponential moving average to enhance stability. The proposed SSC-SR framework works as a plug-and-play paradigm and can be easily applied to existing SR models. Empirical evaluations reveal that our SSC-SR framework delivers substantial enhancements on a variety of benchmark datasets, achieving an average increase of 0.1 dB over EDSR and 0.06 dB over SwinIR. In addition, extensive ablation studies corroborate the effectiveness of each constituent in our SSC-SR framework. Codes are available at https://github.com/Aitical/SSCSR.

Related papers

• Self-Supervised Image Super-Resolution Quality Assessment based on Content-Free Multi-Model Oriented Representation Learning [3.0175628677371935]
  Super-resolution (SR) applied to real-world low-resolution (LR) images often results in complex, irregular degradations.<n>In this work, we introduce a no-reference SR-IQA approach tailored for such highly ill-posed realistic settings.<n>The proposed method enables domain-adaptive IQA for real-world SR applications.
  arXiv  Detail & Related papers  (2026-02-11T11:15:34Z)
• The Double-Edged Sword of Data-Driven Super-Resolution: Adversarial Super-Resolution Models [0.8921166277011348]
  We present AdvSR, a framework demonstrating that adversarial behavior can be embedded directly into SR model weights during training.<n>By jointly optimizing for reconstruction quality and targeted adversarial outcomes, AdvSR produces models that appear benign under standard image quality metrics.<n>These findings highlight a new model-level threat for imaging pipelines, with implications for how practitioners source and validate models in safety-critical applications.
  arXiv  Detail & Related papers  (2026-02-06T23:00:58Z)
• Dual-domain Adaptation Networks for Realistic Image Super-resolution [81.34345637776408]
  Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones.<n>Current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features.<n>We introduce a novel approach, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets.
  arXiv  Detail & Related papers  (2025-11-21T12:57:23Z)
• Your Super Resolution Model is not Enough for Tackling Real-World Scenarios [2.101267270902429]
  We propose a plug-in Scale-Aware Attention Module (SAAM) designed to retrofit modern fixed-scale SR models with the ability to perform arbitrary-scale SR.<n>SAAM employs lightweight, scale-adaptive feature extraction and upsampling, incorporating the Simple parameter-free Attention Module (SimAM) for efficient guidance and gradient variance loss.<n>Our method integrates seamlessly into multiple state-of-the-art SR backbones, delivering competitive or superior performance across a wide range of integer and non-integer scale factors.
  arXiv  Detail & Related papers  (2025-09-08T07:13:58Z)
• NSSR-DIL: Null-Shot Image Super-Resolution Using Deep Identity Learning [0.02932486408310998]
  We present a novel ISR algorithm that is independent of the image dataset to learn the ISR task. We introduce Deep Identity Learning, exploiting the identity relation between the degradation and inverse degradation models. The proposed NSSR-DIL model requires fewer computational resources, at least by an order of 10, and demonstrates a competitive performance on benchmark ISR datasets.
  arXiv  Detail & Related papers  (2024-09-17T03:43:07Z)
• AnySR: Realizing Image Super-Resolution as Any-Scale, Any-Resource [84.74855803555677]
  We introduce AnySR, to rebuild existing arbitrary-scale SR methods into any-scale, any-resource implementation. Our AnySR innovates in: 1) building arbitrary-scale tasks as any-resource implementation, reducing resource requirements for smaller scales without additional parameters; 2) enhancing any-scale performance in a feature-interweaving fashion. Results show that our AnySR implements SISR tasks in a computing-more-efficient fashion, and performs on par with existing arbitrary-scale SISR methods.
  arXiv  Detail & Related papers  (2024-07-05T04:00:14Z)
• ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution [60.90817228730133]
  Single image super-resolution (SISR) is a challenging problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart. Recent approaches are trained on simulated LR images degraded by simplified down-sampling operators. We propose a novel Invertible scale-Conditional Function (ICF) which can scale an input image and then restore the original input with different scale conditions.
  arXiv  Detail & Related papers  (2023-07-24T12:42:45Z)
• CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution [158.2282163651066]
  This paper proposes a continuous implicit attention-in-attention network, called CiaoSR. We explicitly design an implicit attention network to learn the ensemble weights for the nearby local features. We embed a scale-aware attention in this implicit attention network to exploit additional non-local information.
  arXiv  Detail & Related papers  (2022-12-08T15:57:46Z)
• RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection [66.08293086254851]
  We propose a reciprocal learning framework to reinforce the learning of a RefSR network. The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection. We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm.
  arXiv  Detail & Related papers  (2022-11-08T12:39:35Z)
• Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution [37.99541178081113]
  A Content and Degradation SR Network dubbed CDSR is proposed. The proposed CDSR outperforms the existing UDP models and achieves competitive performance on PSNR and SSIM.
  arXiv  Detail & Related papers  (2022-08-29T09:12:39Z)
• Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution [64.15915577164894]
  A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing. HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
  arXiv  Detail & Related papers  (2022-06-07T14:55:32Z)
• SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models [19.17571465274627]
  Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones. We propose a novel single image super-resolution diffusion probabilistic model (SRDiff) SRDiff is optimized with a variant of the variational bound on the data likelihood and can provide diverse and realistic SR predictions.
  arXiv  Detail & Related papers  (2021-04-30T12:31:25Z)

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.