Metraipolis › archive › dc_37a305c3cdc4
PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution — arXiv:2608.30782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30782
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:40.639Z
- SHA-256 of the archived text
1ed0e56184ed60e55c78902528466999e2ff086d519bedcc2c66a8cdf0759b49- Stable URL of this page
https://metraipolis.com/documento/dc_37a305c3cdc4
How to cite
PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution — arXiv:2608.30782 — arXiv (en), https://arxiv.org/abs/2608.30782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37a305c3cdc4 (Metraipolis archive dc_37a305c3cdc4, sha256 1ed0e56184ed60e55c78902528466999e2ff086d519bedcc2c66a8cdf0759b49)
BibTeX
@misc{dc37a305c3cdc4,
title = {PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution — arXiv:2608.30782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37a305c3cdc4; sha256 1ed0e56184ed60e55c78902528466999e2ff086d519bedcc2c66a8cdf0759b49},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.30782 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:48.184Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).