paper-with-me

홈 › Papers

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark

2025-10-14 · Bruno Longarela, Marcos V. Conde, Alvaro Garcia, Radu Timofte arxiv

This paper presents a comprehensive study and benchmark on Efficient Perceptual Super-Resolution (EPSR). While significant progress has been made in efficient PSNR-oriented super resolution, approaches focusing on perceptual quality metrics remain relatively inefficient. Motivated by this gap, we aim to replicate or improve the perceptual results of Real-ESRGAN while meeting strict efficiency constraints: a maximum of 5M parameters and 2000 GFLOPs, calculated for an input size of 960x540 pixels. The proposed solutions were evaluated on a novel dataset consisting of 500 test images of 4K resolution, each degraded using multiple degradation types, without providing the original high-quality counterparts. This design aims to reflect realistic deployment conditions and serves as a diverse and challenging benchmark. The top-performing approach manages to outperform Real-ESRGAN across all benchmark datasets, demonstrating the potential of efficient methods in the perceptual domain. This paper establishes the modern baselines for efficient perceptual super resolution.

📄 PDF Abstract BibTeX arXiv:2510.12765

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

2022-01-17 · Jie Song, Huawei Yi, Wenqian Xu, Xiaohui Li 외

The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-reso…

Image Super-ResolutionSuper-Resolution

The 2018 PIRM Challenge on Perceptual Image Super-resolution

2018-09-20 · Yochai Blau, Roey Mechrez, Radu Timofte, Tomer Michaeli 외

This paper reports on the 2018 PIRM challenge on perceptual super-resolution (SR), held in conjunction with the Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018. In contrast to previous SR chall…

Image RestorationImage Super-ResolutionSuper-ResolutionVideo Quality Assessment

SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution

2017-12-16 · Bingzhe Wu, Haodong Duan, Zhichao Liu, Guangyu Sun

Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convo…

Generative Adversarial NetworkImage Super-ResolutionSSIMSuper-Resolution

The Fourth Challenge on Image Super-Resolution ($\times$4) at NTIRE 2026: Benchmark Results and Method Overview

2026-04-16 · Zheng Chen, Kai Liu, Jingkai Wang, Xianglong Yan 외 arxiv

This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images f…

Image Super-Resolution

A New Super-Resolution Measurement of Perceptual Quality and Fidelity

2023-03-10 · Sheng Cheng

Super-resolution results are usually measured by full-reference image quality metrics or human rating scores. However, these evaluation methods are general image quality measurement, and do not account for the nature of …

Super-Resolution