PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving Real-World Image Super-Resolution (Real-ISR), which is about making blurry or low-quality images clearer while keeping them realistic. They point out that previous methods tried to improve clarity and visual appeal at the same time, which made it hard to balance these goals. To fix this, the authors created PixelIR, a new two-step process that first reconstructs a clear image and then adds realistic details without mixing the two tasks. Their approach is efficient, fast, and performs well on standard tests compared to other methods.
Real-World Image Super-ResolutionFidelityPerceptual QualityImage-Residual FlowFlow MatchingPixel-Space RestorationPSNRSSIMLPIPSCoarse-to-Fine Pyramid Architecture
Authors
Bingtian Qiao, Yue Shi, Yong Guo, Wenjun Zhang, Jiezhang Cao
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.