CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness

• URL: http://arxiv.org/abs/2602.22159v1
• Date: Wed, 25 Feb 2026 18:05:51 GMT
• Title: CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness
• Abstract summary: CASR is a simple yet highly efficient cyclic SR framework that reformulates ultra-magnification as a sequence of in-distribution scale transitions.<n>This design ensures stable inference at arbitrary scales while requiring only a single model.<n>Despite using only a single model, our approach significantly reduces distribution drift, preserves long-range texture consistency, and achieves superior generalization even at extreme magnification.
• Score: 14.01813573738112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and artifacts accumulate sharply. We revisit this challenge from a cross-scale distribution transition perspective and propose CASR, a simple yet highly efficient cyclic SR framework that reformulates ultra-magnification as a sequence of in-distribution scale transitions. This design ensures stable inference at arbitrary scales while requiring only a single model. CASR tackles two major bottlenecks: distribution drift across iterations and patch-wise diffusion inconsistencies. The proposed SDAM module aligns structural distributions via superpixel aggregation, preventing error accumulation, while SARM module restores high-frequency textures by enforcing autocorrelation and embedding LR self-similarity priors. Despite using only a single model, our approach significantly reduces distribution drift, preserves long-range texture consistency, and achieves superior generalization even at extreme magnification.

Related papers

• Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution [80.28905986756685]
  DiMOO-SR is a rarity-aware multimodal discrete diffusion framework for photo-realistic image Super-Resolution.<n>Experiments on widely used real-world SR benchmarks demonstrate that DiMOO-SR achieves competitive perceptual quality with only a few parallel decoding steps.
  arXiv  Detail & Related papers  (2026-07-20T07:01:01Z)
• Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution [69.17533212524447]
  We propose a Difficulty-aware Dynamic Routing ( DDR) strategy that overcomes the rigid, one-size-fits-all processing paradigm.<n>Specifically, we design a difficulty estimator to predict the restoration cost of each input image, enabling automatic assignment to a network of appropriate capacity.<n>Extensive experiments have demonstrated the superior efficiency and effectiveness of the proposed model compared to recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-17T07:49:05Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models [52.648413887350195]
  We propose Stage-Aware RoPE Remapping to suppress global repetition, local repetition, and detail degradation.<n>We also propose Entropy-Driven Adaptive Attention, which quantifies dispersion via a resolution-invariant normalized entropy.<n>Our method consistently outperforms prior resolution-extrapolation methods in both structural coherence and fine-detail fidelity.
  arXiv  Detail & Related papers  (2026-05-11T06:14:38Z)
• SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation [10.518150741228862]
  SlimDiffSR is a lightweight and efficient diffusion-based framework for real-world remote sensing image super-resolution.<n>It attains up to $200times$ inference acceleration and a $20times$ reduction in model parameters compared with multi-step diffusion models.
  arXiv  Detail & Related papers  (2026-05-04T03:54:54Z)
• Bridging Restoration and Generation Manifolds in One-Step Diffusion for Real-World Super-Resolution [22.963799508399365]
  Recent single-step distillation accelerates inference but faces a stark perception-distortion trade-off.<n>We present Adaptive Inversion and Degradation-aware Sampling for Real-ISR (IDaS-SR)<n>IDaS-SR is a one-step framework bridging the deterministic restoration and generation bottlenecks.
  arXiv  Detail & Related papers  (2026-04-27T07:43:00Z)
• LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction [4.609499769793957]
  Diffusion-based image super-resolution (SR) aims to reconstruct high-resolution (HR) images from corresponding low-resolution (LR) observations.<n>The state-of-the-art residual-shifting diffusion framework efficient 4-step inference suffers from severe degradation performance in compact sampling trajectories.<n>We propose a prior-enhanced efficient diffusion framework to address these issues.
  arXiv  Detail & Related papers  (2026-03-22T03:52:38Z)
• Single Image Super-Resolution via Bivariate `A Trous Wavelet Diffusion [5.897882149801945]
  Super resolution (SR) models need to be able to recover high frequency structure without introducing artifacts.<n>We introduce BATDiff, which provides structured cross scale guidance during the generative process.<n>It produces sharper and more structurally consistent reconstructions than existing diffusion and non diffusion baselines.
  arXiv  Detail & Related papers  (2026-03-07T14:36:37Z)
• AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution [16.90182090355781]
  Visual autoregressive models offer stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction.<n>But their application remains underexplored and faces two critical challenges: locality-biased attention, and residual-only supervision.<n>We propose a globally consistent visual autoregressive framework tailored for image super-resolution.
  arXiv  Detail & Related papers  (2026-02-28T10:39:06Z)
• InfScene-SR: Spatially Continuous Inference for Arbitrary-Size Image Super-Resolution [3.6762434952581713]
  InfScene-SR is a framework enabling spatially continuous super-resolution for large, arbitrary scenes.<n>We adapt the iterative refinement process of diffusion models with a novel guided and variance-corrected fusion mechanism.
  arXiv  Detail & Related papers  (2026-02-23T11:34:59Z)
• OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution [25.29121925794166]
  Arbitrary-scale super-resolution (ASSR) overcomes the limitation of traditional super-resolution (SR) methods that operate only at fixed scales (e.g., 4x)<n>Recent diffusion-based realistic image super-resolution (Real-ISR) models leverage powerful pre-trained diffusion priors and show impressive results at the 4x setting.<n>We propose OmniScaleSR, a diffusion-based realistic arbitrary-scale SR framework designed to achieve both high fidelity and high realism.
  arXiv  Detail & Related papers  (2025-12-04T11:50:17Z)
• OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot [4.990334603434127]
  OBS-Diff is a novel one-shot pruning framework that enables accurate and training-free compression of large-scale text-to-image diffusion models.<n>Extensive experiments show that OBS-Diff achieves state-of-the-art one-shot pruning for diffusion models, delivering inference acceleration with minimal degradation in visual quality.
  arXiv  Detail & Related papers  (2025-10-08T08:19:15Z)
• UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation [104.59740403500132]
  Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance.<n>We propose a unified modality-relax segmentation network (UniMRSeg) through hierarchical self-supervised compensation (HSSC)<n>Our approach hierarchically bridges representation gaps between complete and incomplete modalities across input, feature and output levels.
  arXiv  Detail & Related papers  (2025-09-19T17:29:25Z)
• Rotation Equivariant Arbitrary-scale Image Super-Resolution [62.41329042683779]
  The arbitrary-scale image super-resolution (ASISR) aims to achieve arbitrary-scale high-resolution recoveries from a low-resolution input image.<n>We make efforts to construct a rotation equivariant ASISR method in this study.
  arXiv  Detail & Related papers  (2025-08-07T08:51:03Z)
• Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling [50.34513854725803]
  Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors.<n>We propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-03-09T13:43:57Z)
• Latent Diffusion, Implicit Amplification: Efficient Continuous-Scale Super-Resolution for Remote Sensing Images [7.920423405957888]
  E$2$DiffSR achieves superior objective metrics and visual quality compared to the state-of-the-art SR methods. It reduces the inference time of diffusion-based SR methods to a level comparable to that of non-diffusion methods.
  arXiv  Detail & Related papers  (2024-10-30T09:14:13Z)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step [119.18813219518042]
  Super-resolution (SR) methods based on diffusion models exhibit promising results. But their practical application is hindered by the substantial number of required inference steps. We propose a simple yet effective method for achieving single-step SR generation, named SinSR.
  arXiv  Detail & Related papers  (2023-11-23T16:21:29Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• 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.