mlsanityData to 14 Oct 2026

Versatile Recompression-Aware Perceptual Image Super-Resolution

arXiv 2511.18090 ↗First posted 22 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission. Ignoring recompression is suboptimal as the downstream codec might add additional artifacts to restored images. However, jointly optimizing SR and recompression is challenging, as the codecs are not differentiable and vary in configuration. In this paper, we present Versatile Recompression-Aware Perceptual Super-Resolution (VRPSR), which makes existing perceptual SR aware of versatile compression. First, we formulate compression as conditional text-to-image generation and utilize a pre-trained diffusion model to build a generalizable codec simulator. Next, we propose a set of training techniques tailored for perceptual SR, including optimizing the simulator using perceptual targets and adopting slightly compressed images as the training target. Empirically, our VRPSR achieves 10% - 40% bitrate savings based on Real-ESRGAN and S3Diff under H.264/H.265/H.266 single-picture (intra) compression. Besides, our VRPSR facilitates joint optimization of SR and the post-processing model after recompression.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 22 Nov 2025.

Builds on

32 of 42 references.

References · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  10. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  12. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
20 more
  1. 2018Variational image compression with a scale hyperpriorcited by 935
  2. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  3. 2023Adversarial Diffusion Distillationcited by 759
  4. 2017The Perception-Distortion Tradeoffcited by 587
  5. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  7. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  8. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  9. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  10. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 238
  11. 2021Invertible Image Signal Processingcited by 94
  12. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priorscited by 69
  13. 2014DenseNet: Implementing Efficient ConvNet Descriptor Pyramidscited by 66
  14. 2021Self-Conditioned Probabilistic Learning of Video Rescalingcited by 19
  15. 2022Preprocessing Enhanced Image Compression for Machine Visioncited by 18
  16. 2023Differentiable JPEG: The Devil is in the Detailscited by 13
  17. 2023Self-Asymmetric Invertible Network for Compression-Aware Image Rescalingcited by 9
  18. 2024Sandwiched Compression: Repurposing Standard Codecs with Neural Network Wrapperscited by 7
  19. 2023Differentiable bit-rate estimation for neural-based video codec enhancementcited by 3
  20. 2024Standard compliant video coding using low complexity, switchable neural wrapperscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards image compression with perfect realism at ultra-low bitrates
  2. 2024UniMIC: Towards Universal Multi-modality Perceptual Image Compression
  3. 2023Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
  4. 2026PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution
  5. 2025A Lightweight Model for Perceptual Image Compression via Implicit Priors
  6. 2025Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
  7. 2024Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors
  8. 2025DP2O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution