mlsanityData to 7 Oct 2026

Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution

arXiv 2506.07813 ↗First posted 9 Jun 2025cs.CV cs.AIcited by 1

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches based on regression-based or generative models have shown promising results but often suffer from scale inconsistency due to their single-stage formulation, which must handle a wide range of scaling factors simultaneously. To address this, we propose CasArbi, a self-cascaded diffusion framework for arbitrary-scale image super-resolution. CasArbi decomposes varying scaling factors into smaller sequential steps, progressively enhancing the image resolution at each step with seamless transitions for arbitrary scales. CasArbi leverages a coordinate-conditioned diffusion model for learning continuous image representations and adopts self-consistency guidance to generate scale-consistent details at inference time. Extensive experiments show that CasArbi outperforms existing methods in both perceptual and distortion metrics and demonstrates superior scale consistency across diverse arbitrary-scale super-resolution benchmarks. Our code is available at https://github.com/junseo88/CasArbi.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 59 of its 75 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

59 of 75 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Latent Diffusion, Implicit Amplification: Efficient Continuous-Scale Super-Resolution for Remote Sensing Images30 Oct
  2. 2024Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder15 Mar
  3. 2023Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance27 Dec
  4. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting23 Jul
  5. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
  6. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement3 Apr
  7. 2023Implicit Diffusion Models for Continuous Super-Resolution29 Mar
  8. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  9. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep

Other references · 50

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2022Video Diffusion Modelscited by 2,280
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2015Variational Inference with Normalizing Flowscited by 2,161
  10. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  11. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  12. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
38 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2018On the Spectral Bias of Neural Networkscited by 1,321
  4. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  8. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  9. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  10. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  11. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  12. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  13. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  14. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  15. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  16. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  17. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  18. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 343
  19. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  20. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 290
  21. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  22. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  23. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 180
  24. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  25. 2019Feedback Network for Image Super-Resolutioncited by 155
  26. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  27. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  28. 2021Local Texture Estimator for Implicit Representation Functioncited by 126
  29. 2023Relay Diffusion: Unifying diffusion process across resolutions for image synthesiscited by 78
  30. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  31. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  32. 2020Learning A Single Network for Scale-Arbitrary Super-Resolutioncited by 65
  33. 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolutioncited by 51
  34. 2024Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptationcited by 50
  35. 2018A Fully Progressive Approach to Single-Image Super-Resolutioncited by 46
  36. 2021Implicit Transformer Network for Screen Content Image Continuous Super-Resolutioncited by 46
  37. 2021SRWarp: Generalized Image Super-Resolution under Arbitrary Transformationcited by 26
  38. 2022Arbitrary-Scale Image Synthesiscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
  2. 2024Diffusion Models, Image Super-Resolution And Everything: A Survey
  3. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step
  4. 2024CasSR: Activating Image Power for Real-World Image Super-Resolution
  5. 2026Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
  6. 2024You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
  7. 2026TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution
  8. 2026Fast Image Super-Resolution via Consistency Rectified Flow