Evaluating and Preserving High-level Fidelity in Super-Resolution

• URL: http://arxiv.org/abs/2512.07037v2
• Date: Tue, 09 Dec 2025 10:10:47 GMT
• Title: Evaluating and Preserving High-level Fidelity in Super-Resolution
• Authors: Josep M. Rocafort, Shaolin Su, Alexandra Gomez-Villa, Javier Vazquez-Corral,
• Abstract summary: Super-Resolution (SR) models are achieving impressive effects in reconstructing details and delivering pleasant visually outputs.<n>However, the overpowering generative ability can sometimes hallucinate and thus change the image content.<n>This type of high-level change can be easily identified by humans yet not well-studied in existing low-level image quality metrics.
• Score: 50.65679806442527
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent image Super-Resolution (SR) models are achieving impressive effects in reconstructing details and delivering visually pleasant outputs. However, the overpowering generative ability can sometimes hallucinate and thus change the image content despite gaining high visual quality. This type of high-level change can be easily identified by humans yet not well-studied in existing low-level image quality metrics. In this paper, we establish the importance of measuring high-level fidelity for SR models as a complementary criterion to reveal the reliability of generative SR models. We construct the first annotated dataset with fidelity scores from different SR models, and evaluate how state-of-the-art (SOTA) SR models actually perform in preserving high-level fidelity. Based on the dataset, we then analyze how existing image quality metrics correlate with fidelity measurement, and further show that this high-level task can be better addressed by foundation models. Finally, by fine-tuning SR models based on our fidelity feedback, we show that both semantic fidelity and perceptual quality can be improved, demonstrating the potential value of our proposed criteria, both in model evaluation and optimization. We will release the dataset, code, and models upon acceptance.

Related papers

• FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution [87.57784204422218]
  Reinforcement Learning with Human Feedback has proven effective in image generation field guided by reward models to align human preferences.<n>We propose a Fine-grained Perceptual Reward Model (FinPercep-RM) based on ancoder-Decoder architecture.<n>While providing a global quality score, it also generates a Perceptual Degradation Map that spatially localizes and quantifies local defects.
  arXiv  Detail & Related papers  (2025-12-27T16:55:21Z)
• Q-REAL: Towards Realism and Plausibility Evaluation for AI-Generated Content [71.46991494014382]
  We introduce Q-Real, a novel dataset for fine-grained evaluation of realism and plausibility in AI-generated images.<n>Q-Real consists of 3,088 images generated by popular text-to-image models.<n>We construct Q-Real Bench to evaluate them on two tasks: judgment and grounding with reasoning.
  arXiv  Detail & Related papers  (2025-11-21T02:43:17Z)
• 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)
• IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond [56.99331967165238]
  Blind Face Restoration (BFR) addresses the challenge of reconstructing degraded low-quality (LQ) facial images into high-quality (HQ) outputs.<n>We propose a novel framework that incorporates an Image Quality Prior (IQP) derived from No-Reference Image Quality Assessment (NR-IQA) models.<n>Our method outperforms state-of-the-art techniques across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-03-12T11:39:51Z)
• IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models [0.5356944479760104]
  We propose methods to integrate image quality assessment (IQA) models into diffusion-based generators.<n>We show that diffusion models can learn complex qualitative relationships from both IQA models' outputs and internal activations.<n>We introduce IQA-Adapter, a novel framework that conditions generation on target quality levels by learning the implicit relationship between images and quality scores.
  arXiv  Detail & Related papers  (2024-12-02T18:40:19Z)
• Study of Subjective and Objective Quality in Super-Resolution Enhanced Broadcast Images on a Novel SR-IQA Dataset [4.770359059226373]
  Super-Resolution (SR), a key consumer technology, is essential to display low-quality broadcast content on high-resolution screens in full-screen format. evaluating the quality of SR images generated from low-quality sources, such as SR-enhanced broadcast content, is challenging. We introduce a new IQA dataset for SR broadcast images in both 2K and 4K resolutions.
  arXiv  Detail & Related papers  (2024-09-26T01:07:15Z)
• When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents [92.45867913876691]
  No-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality.<n>We show that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement.
  arXiv  Detail & Related papers  (2024-03-11T03:35:41Z)
• Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment [78.21609845377644]
  We propose a novel class of state-of-the-art (SOTA) generative model, which exhibits the capability to model intricate relationships.<n>We devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images.<n>Two visual evaluation branches are designed to comprehensively analyze the obtained high-level feature information.
  arXiv  Detail & Related papers  (2024-02-22T09:39:46Z)
• A comparative analysis of SRGAN models [0.0]
  We evaluate the performance of SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images. Some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine.
  arXiv  Detail & Related papers  (2023-07-18T17:35:45Z)
• Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric [0.0]
  Super-resolution (SR) methods can improve overall image and video quality and create new possibilities for content analysis. But the SR mainstream focuses primarily on increasing the naturalness of the resulting image.
  arXiv  Detail & Related papers  (2022-03-16T20:13:35Z)

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.