Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark

• URL: http://arxiv.org/abs/2510.12765v1
• Date: Tue, 14 Oct 2025 17:45:22 GMT
• Title: Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
• Authors: Bruno Longarela, Marcos V. Conde, Alvaro Garcia, Radu Timofte,
• Abstract summary: We aim to replicate or improve the perceptual results of Real-ESRGAN while meeting strict efficiency constraints.<n>The proposed solutions were evaluated on a novel dataset consisting of 500 test images of 4K resolution, each degraded using multiple degradation types.<n>The top-performing approach manages to outperform Real-ESRGAN across all benchmark datasets.
• Score: 53.56717645904575
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report [59.64053782297197]
  This paper reviews the AIM 2025 Efficient Real-World Deblurring using Single Images Challenge.<n>The challenge is based on a new test set based on the well known RSBlur dataset.<n>The top-performing approach achieved a PSNR of 31.1298 dB, showcasing the potential of efficient methods in this domain.
  arXiv  Detail & Related papers  (2025-10-14T17:57:04Z)
• Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark [2.7961815663180425]
  Super-resolution for License Plate Recognition (LPR) has sought to address challenges posed by low-resolution (LR) and degraded images in surveillance, traffic monitoring, and forensic applications.<n>We introduce UFPR-SR-Plates, a novel dataset containing 10,000 tracks with 100,000 paired low and high-resolution license plate images captured under real-world conditions.<n>We establish a benchmark using multiple sequential LR and high-resolution (HR) images per vehicle -- five of each -- and two state-of-the-art models for super-resolution of license plates.
  arXiv  Detail & Related papers  (2025-05-09T19:37:57Z)
• Learning to Be a Transformer to Pinpoint Anomalies [12.442574943138794]
  Recent Industrial Anomaly Detection and (IADS) methods process low-resolution images, e.g., 224x224 pixels, obtained by downsampling the original input images.<n>We propose a novel Teacher--Student paradigm to leverage strong pre-trained features while processing high-resolution input images very efficiently.<n>Our method can spot anomalies from high-resolution images and runs way faster than competitors.
  arXiv  Detail & Related papers  (2024-07-04T17:59:26Z)
• IG-CFAT: An Improved GAN-Based Framework for Effectively Exploiting Transformers in Real-World Image Super-Resolution [2.1561701531034414]
  Recently, composite fusion attention transformer (CFAT) outperformed previous state-of-the-art (SOTA) models in classic image super-resolution.<n>In this paper, we propose a novel GAN-based framework by incorporating the CFAT model to effectively exploit the performance of transformers in real-world image super-resolution.
  arXiv  Detail & Related papers  (2024-06-19T20:21:26Z)
• From Blurry to Brilliant Detection: YOLO-Based Aerial Object Detection with Super Resolution [3.5044007821404635]
  Aerial object detection presents challenges from small object sizes, high density clustering, and image quality degradation from distance and motion blur.<n>B2BDet addresses this with a two-stage framework that applies domain-specific super-resolution during inference, followed by detection using an enhanced YOLOv5 architecture.<n>The approach combines aerial-optimized SRGAN fine-tuning with architectural innovations including an Efficient Attention Module (EAM) and Cross-Layer Feature Pyramid Network (CLFPN)
  arXiv  Detail & Related papers  (2024-01-26T05:50:58Z)
• EFaR 2023: Efficient Face Recognition Competition [51.77649060180531]
  The paper presents the summary of the Efficient Face Recognition Competition (EFaR) held at the 2023 International Joint Conference on Biometrics (IJCB 2023) The competition received 17 submissions from 6 different teams. The submitted solutions are ranked based on a weighted score of the achieved verification accuracies on a diverse set of benchmarks, as well as the deployability given by the number of floating-point operations and model size.
  arXiv  Detail & Related papers  (2023-08-08T09:58:22Z)
• Semantically Accurate Super-Resolution Generative Adversarial Networks [2.0454959820861727]
  We propose a novel architecture and domain-specific feature loss to increase the performance of semantic segmentation. We show the proposed approach improves perceived image quality as well as quantitative segmentation accuracy across all prediction classes. This work demonstrates that jointly considering image-based and task-specific losses can improve the performance of both, and advances the state-of-the-art in semantic-aware super-resolution of aerial imagery.
  arXiv  Detail & Related papers  (2022-05-17T23:05:27Z)
• Fully Quantized Image Super-Resolution Networks [81.75002888152159]
  We propose a Fully Quantized image Super-Resolution framework (FQSR) to jointly optimize efficiency and accuracy. We apply our quantization scheme on multiple mainstream super-resolution architectures, including SRResNet, SRGAN and EDSR. Our FQSR using low bits quantization can achieve on par performance compared with the full-precision counterparts on five benchmark datasets.
  arXiv  Detail & Related papers  (2020-11-29T03:53:49Z)
• AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results [222.26973543552327]
  This paper reviews the AIM 2020 challenge on efficient single image super-resolution. The challenge task was to super-resolve an input image with a magnification factor x4. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption.
  arXiv  Detail & Related papers  (2020-09-15T09:25:51Z)
• AR-Net: Adaptive Frame Resolution for Efficient Action Recognition [70.62587948892633]
  Action recognition is an open and challenging problem in computer vision. We propose a novel approach, called AR-Net, that selects on-the-fly the optimal resolution for each frame conditioned on the input for efficient action recognition.
  arXiv  Detail & Related papers  (2020-07-31T01:36:04Z)

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.