Perceptual Quality Optimization of Image Super-Resolution

• URL: http://arxiv.org/abs/2602.21482v1
• Date: Wed, 25 Feb 2026 01:17:24 GMT
• Title: Perceptual Quality Optimization of Image Super-Resolution
• Authors: Wei Zhou, Yixiao Li, Hadi Amirpour, Xiaoshuai Hao, Jiang Liu, Peng Wang, Hantao Liu,
• Abstract summary: Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or perceptual priors.<n>We propose an textitEfficient Perceptual Bi-directional Attention Network (Efficient-PBAN) that explicitly optimize SR towards human-preferred quality.
• Score: 31.948003749760105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual quality. To address this issue, we propose an \textit{Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN)} that explicitly optimizes SR towards human-preferred quality. Unlike patch-based quality models, Efficient-PBAN avoids extensive patch sampling and enables efficient image-level perception. The proposed framework is trained on our self-constructed SR quality dataset that covers a wide range of state-of-the-art SR methods with corresponding human opinion scores. Using this dataset, Efficient-PBAN learns to predict perceptual quality in a way that correlates strongly with subjective judgments. The learned metric is further integrated into SR training as a differentiable perceptual loss, enabling closed-loop alignment between reconstruction and perceptual assessment. Extensive experiments demonstrate that our approach delivers superior perceptual quality. Code is publicly available at https://github.com/Lighting-YXLI/Efficient-PBAN.

Related papers

• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment [61.27648290203618]
  We propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA.<n>PBAN is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module.<n>Our proposed PBAN outperforms state-of-the-art quality assessment methods.
  arXiv  Detail & Related papers  (2025-09-08T08:39:45Z)
• Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models [0.026861992804651083]
  This paper introduces a robust framework for identifying the most trustworthy SR sample from a diffusion-generated set.<n>We propose a novel Trustworthiness Score (TWS) a hybrid metric that quantifies SR reliability based on semantic similarity.<n>By aligning outputs with human expectations and semantic correctness, this work sets a new benchmark for trustworthiness in generative SR.
  arXiv  Detail & Related papers  (2025-06-25T21:00:44Z)
• One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation [53.24542646616045]
  We propose VPD-SR, a novel visual perception diffusion distillation framework specifically designed for image super-resolution (SR) generation.<n>VPD-SR consists of two components: Explicit Semantic-aware Supervision (ESS) and High-frequency Perception (HFP) loss.<n>The proposed VPD-SR achieves superior performance compared to both previous state-of-the-art methods and the teacher model with just one-step sampling.
  arXiv  Detail & Related papers  (2025-06-03T08:28:13Z)
• Augmenting Perceptual Super-Resolution via Image Quality Predictors [10.586351810396645]
  Super-resolution (SR) is inherently ill-posed, inducing a distribution of plausible solutions for every input.<n>In this work, we explore an alternative: utilizing powerful non-reference image quality assessment (NR-IQA) models in the SR context.<n>Our results demonstrate a more human-centric perception-distortion tradeoff, focusing less on non-perceptual pixel-wise distortion, instead improving the balance between perceptual fidelity and human-tuned NR-IQA measures.
  arXiv  Detail & Related papers  (2025-04-25T17:47:38Z)
• Learning Correction Errors via Frequency-Self Attention for Blind Image Super-Resolution [1.734165485480267]
  We introduce a novel blind SR approach that focuses on Learning Correction Errors (LCE) Within an SR network, we jointly optimize SR performance by utilizing both the original LR image and the frequency learning of the CLR image. Our approach effectively addresses the challenges associated with degradation estimation and correction errors, paving the way for more accurate blind image SR.
  arXiv  Detail & Related papers  (2024-03-12T07:58:14Z)
• Learning from Multi-Perception Features for Real-Word Image Super-resolution [87.71135803794519]
  We propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information. We also introduce a contrastive regularization term (CR) that improves the model's learning capability.
  arXiv  Detail & Related papers  (2023-05-26T07:35:49Z)
• Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution [64.15915577164894]
  A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing. HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
  arXiv  Detail & Related papers  (2022-06-07T14:55:32Z)
• Textural-Structural Joint Learning for No-Reference Super-Resolution Image Quality Assessment [59.91741119995321]
  We develop a dual stream network to jointly explore the textural and structural information for quality prediction, dubbed TSNet. By mimicking the human vision system (HVS) that pays more attention to the significant areas of the image, we develop the spatial attention mechanism to make the visual-sensitive areas more distinguishable. Experimental results show the proposed TSNet predicts the visual quality more accurate than the state-of-the-art IQA methods, and demonstrates better consistency with the human's perspective.
  arXiv  Detail & Related papers  (2022-05-27T09:20:06Z)

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.