PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution

• URL: http://arxiv.org/abs/2608.30782v1
• Date: Mon, 31 Aug 2026 13:39:54 GMT
• Title: PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution
• Abstract summary: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details.<n>We propose PixelIR, a fidelity-perception decoupling framework built upon pixel-space image-residual flow matching.<n>Experiments show that PixelIR achieves leading PSNR, SSIM, and LPIPS on both RealSR and DRealSR.
• Score: 28.787313933850687
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existing Real-ISR methods largely optimize fidelity and perceptual quality within a shared network, causing the two objectives to interfere throughout training and making their balance difficult to control. Recent one-step methods reduce sampling steps, yet often inherit both this coupled optimization behavior and the expensive high-resolution backbone of their multi-step predecessors. We argue that efficient Real-ISR requires not only a shorter sampling trajectory, but also specialized modeling of faithful reconstruction and perceptual detail synthesis. Based on this insight, we propose PixelIR, a fidelity-perception decoupling framework built upon pixel-space image-residual flow matching. PixelIR first learns an image flow that maps the degraded observation to a faithful reconstruction. Then, a residual flow synthesizes the missing perceptual details from noise without repeatedly relearning or overwriting the complete restoration solution. We further distill the teacher into a deployment-oriented one-step student within a coarse-to-fine pyramid architecture. Extensive experiments show that PixelIR achieves leading PSNR, SSIM, and LPIPS on both RealSR and DRealSR. The final model completes pixel-space restoration in a single evaluation with only 32.9M parameters, 89.7G MACs, and 8.5ms latency, demonstrating a strong practical fidelity-perception-efficiency balance.

Related papers

• Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration [3.901664292361698]
  PCFlow is a unified framework that parameterizes a continuous transport from degraded observations to clean targets.<n>It achieves competitive performance across diverse restoration tasks at a fraction of traditional computational costs.
  arXiv  Detail & Related papers  (2026-08-11T06:37:10Z)
• MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution [50.60539317126614]
  MeanSR learns an LR-conditioned average velocity field to directly capture the finite-time transition from noisy inputs to plausible HR outputs.<n>Experiments show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency.
  arXiv  Detail & Related papers  (2026-08-10T10:33:18Z)
• Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention [66.63806505114263]
  Existing Real-ISR methods inherit the dense latent representations and quadratic-cost global modeling paradigm.<n>We argue that the key bottleneck lies in excessive token redundancy and costly token interactions during high-resolution restoration.<n>We introduce a linear-attention DiT with LoRA fine-tuning, enabling efficient high-resolution restoration with linear-complexity token mixing.
  arXiv  Detail & Related papers  (2026-05-22T10:07:02Z)
• Fast Image Super-Resolution via Consistency Rectified Flow [65.54302099728712]
  Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR)<n>Recent efforts have introduced few- or single-step solutions, but existing methods inefficiently model the process from noisy input.<n>We propose FlowSR, a novel approach that reformulates the SR problem as a rectified flow from low-resolution (LR) to high-resolution (HR) images.
  arXiv  Detail & Related papers  (2026-05-12T16:42:38Z)
• Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution [79.35296000454694]
  Diffusion-based super-resolution can synthesize rich details, but models trained on synthetic paired data often fail on real-world LR images.<n>We propose Bird-SR, a reward-guided diffusion framework that formulates super-resolution as trajectory-level preference optimization.<n>Experiments on real-world SR benchmarks demonstrate that Bird-SR consistently outperforms state-of-the-art methods in perceptual quality.
  arXiv  Detail & Related papers  (2026-02-05T19:21:45Z)
• Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns [4.977925450373957]
  We propose a novel TripleGAN framework for training super-resolution reconstruction models.<n>The framework learns real-world degradation patterns from LR observations and synthesizes datasets with corresponding degradation characteristics.<n>Our method exhibits clear advantages in quantitative metrics while maintaining sharp reconstructions without over-smoothing artifacts.
  arXiv  Detail & Related papers  (2025-06-20T14:24:48Z)
• Co-learning Single-Step Diffusion Upsampler and Downsampler with Two Discriminators and Distillation [28.174638880324014]
  Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts.<n>We propose a co-learning framework that jointly optimize a single-step diffusion-based upsampler and a learnable downsampler.
  arXiv  Detail & Related papers  (2024-10-10T07:12:46Z)
• Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem [23.833099288826045]
  Training Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores. However, they often results in blurry images due to insufficient recovery of high-frequency details. We propose a novel method that incorporates Multi-Objective Optimization (MOO) into the training process of SISR models to balance perceptual quality and distortion.
  arXiv  Detail & Related papers  (2024-09-05T02:14:04Z)
• LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond [75.37541439447314]
  Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. This paper proposes a linearly-assembled pixel-adaptive regression network (LAPAR) to strike a sweet spot of deep model complexity and resulting SISR quality.
  arXiv  Detail & Related papers  (2021-05-21T15:47:18Z)
• 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)

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.