AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution

• URL: http://arxiv.org/abs/2503.07748v1
• Date: Mon, 10 Mar 2025 18:03:18 GMT
• Title: AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution
• Authors: Cansu Korkmaz, Nancy Mehta, Radu Timofte,
• Abstract summary: AdaptSR is a low-rank adaptation framework that efficiently repurposes bi-cubic-trained SR models for real-world tasks.<n>Our experiments demonstrate that AdaptSR outperforms GAN and diffusion-based SR methods by up to 4 dB in PSNR and 2% in perceptual scores on real SR benchmarks.
• Score: 50.584551250242235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recovering high-frequency details and textures from low-resolution images remains a fundamental challenge in super-resolution (SR), especially when real-world degradations are complex and unknown. While GAN-based methods enhance realism, they suffer from training instability and introduce unnatural artifacts. Diffusion models, though promising, demand excessive computational resources, often requiring multiple GPU days, even for single-step variants. Rather than naively fine-tuning entire models or adopting unstable generative approaches, we introduce AdaptSR, a low-rank adaptation (LoRA) framework that efficiently repurposes bicubic-trained SR models for real-world tasks. AdaptSR leverages architecture-specific insights and selective layer updates to optimize real SR adaptation. By updating only lightweight LoRA layers while keeping the pretrained backbone intact, it captures domain-specific adjustments without adding inference cost, as the adapted layers merge seamlessly post-training. This efficient adaptation not only reduces memory and compute requirements but also makes real-world SR feasible on lightweight hardware. Our experiments demonstrate that AdaptSR outperforms GAN and diffusion-based SR methods by up to 4 dB in PSNR and 2% in perceptual scores on real SR benchmarks. More impressively, it matches or exceeds full model fine-tuning while training 92% fewer parameters, enabling rapid adaptation to real SR tasks within minutes.

Related papers

• Enhanced Super-Resolution Training via Mimicked Alignment for Real-World Scenes [51.92255321684027]
  We propose a novel plug-and-play module designed to mitigate misalignment issues by aligning LR inputs with HR images during training. Specifically, our approach involves mimicking a novel LR sample that aligns with HR while preserving the characteristics of the original LR samples. We comprehensively evaluate our method on synthetic and real-world datasets, demonstrating its effectiveness across a spectrum of SR models.
  arXiv  Detail & Related papers  (2024-10-07T18:18:54Z)
• 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)
• Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning [45.13580581290495]
  This work introduces a novel "Low-Res Leads the Way" (LWay) training framework to enhance the adaptability of SR models to real-world images. Our approach utilizes a low-resolution (LR) reconstruction network to extract degradation embeddings from LR images, merging them with super-resolved outputs for LR reconstruction. Our training regime is universally compatible, requiring no network architecture modifications, making it a practical solution for real-world SR applications.
  arXiv  Detail & Related papers  (2024-03-05T02:29:18Z)
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach [58.57026686186709]
  We introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR) CFSR inherits the advantages of both convolution-based and transformer-based approaches. Experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance.
  arXiv  Detail & Related papers  (2024-01-11T03:08:00Z)
• Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction [62.955327005837475]
  Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
  arXiv  Detail & Related papers  (2023-10-29T13:58:57Z)
• S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution [5.617008573997855]
  A light-weight transformer-based SR model (S2R transformer) and a novel coarse-to-fine training strategy are proposed. The proposed S2R outperforms other single-image SR models in ideal SR condition with only 578K parameters. It can achieve better visual results than regular blind SR models in blind fuzzy conditions with only 10 gradient updates.
  arXiv  Detail & Related papers  (2023-08-16T04:27:44Z)
• DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution [15.694407977871341]
  Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels. We propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR.
  arXiv  Detail & Related papers  (2022-12-15T04:34:57Z)
• Blind Super-Resolution for Remote Sensing Images via Conditional Stochastic Normalizing Flows [14.882417028542855]
  We propose a novel blind SR framework based on the normalizing flow (BlindSRSNF) to address the above problems. BlindSRSNF learns the conditional probability distribution over the high-resolution image space given a low-resolution (LR) image by explicitly optimizing the variational bound on the likelihood. We show that the proposed algorithm can obtain SR results with excellent visual perception quality on both simulated LR and real-world RSIs.
  arXiv  Detail & Related papers  (2022-10-14T12:37:32Z)
• Frequency Consistent Adaptation for Real World Super Resolution [64.91914552787668]
  We propose a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying Super-Resolution (SR) methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding Low-Resolution (LR) images. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models.
  arXiv  Detail & Related papers  (2020-12-18T08:25:39Z)
• Characteristic Regularisation for Super-Resolving Face Images [81.84939112201377]
  Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery. Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data. This renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution. We formulate a method that joins the advantages of conventional SR and UDA models.
  arXiv  Detail & Related papers  (2019-12-30T16:27:24Z)

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.