A Subjective Study on a New Sharpness Informed Class of Metrics

Uditangshu Aurangabadkar; Vibhoothi Vibhoothi; Darren Ramsook; Anil Kokaram

eess.IVAug 14, 2026

A Subjective Study on a New Sharpness Informed Class of Metrics

Authors: Uditangshu Aurangabadkar, Vibhoothi Vibhoothi, Darren Ramsook, Anil Kokaram

Organizations: Sigmedia Group, Department of Electronic and Electrical Engineering, Trinity College Dublin, Dublin, Ireland

Abstract

Perceptual loss functions in Deep Neural Network (DNN) deblurring architectures improve the overall quality of restored images. However, few focus on explicitly targeting sharpness in the restorations. We conduct a subjective study of models trained with and without losses which explicitly target sharpness using a four-protocol approach, exploring preferred sharpness levels and effects on image quality. We introduce a novel dataset of images with uniform sharpness increments along with Difference Mean Opinion Scores (DMOS). Additionally, we propose a novel class of Sharpness Informed (SI) Image Quality Assessment (IQA) metrics which properly penalize over-sharpening. Our new SI-PSNR metric outperforms all other PSNR variants in terms of correlation statistics on IQA benchmarking datasets. We show that, on average, images restored using a sharpness-aware composite loss are preferred in 67% of binarized comparisons, as opposed to losses that do not explicitly target sharpness.

Figures & tables

Fig. 1 : Ringing Map generated using Ringing Detection Ratio ( $\alpha$ ) with a patch size of 4 $\times$ 4 . Left to Right: GT image, Over-sharpened image, Ringing Detection Heatmap. Areas in red (mostly edges) correspond to heavy ringing which are penalized more than areas in blue (flat patches).

Fig. 2 : Sharpness ( $Q$ ) Comparison of Reference Image and Sharpened Image . Images were sharpened to their preferred sharpness levels, showing that subjects preferred sharper images overall, as compared to the reference image.

Fig. 3 : Example of restorations from different DNN-based deblurring mechanisms with different losses . (Top, Bottom): Images restored using ARKNet [ 6 ] and XY-Deblur [ 15 ] . (Left, Right): Images restored using $\mathcal{L}$ and $\mathcal{L}_{c}$ . Images restored with $\mathcal{L}_{c}$ from both deblurring methods produce slightly sharper edges, resulting in aesthetically better images.

Fig. 4 : Comparison of MOS for images restored with separate losses averaged over two separate DNN models: ARKNet and XY-Deblur . Red dots higher than black dots denote that subjects preferred images restored with $\mathcal{L}_{c}$ rather than $\mathcal{L}$ , showing that subjects preferred slightly sharper restorations.

Panel of Figure 5 — Fig. 5 : Example of an image restored with composite loss $\mathcal{L}_{c}$ (SI-PSNR = 27.26) and standard loss $\mathcal{L}$ (SI-PSNR = 35.15). Such images were shown to subjects within the framework of Protocol 2, wherein they were asked to select the sharper of the two.

Dataset		SSIM [ 3 ]	LPIPS [ 5 ]	VIF [ 22 ]	GSSIM [ 21 ]	$Q$ [ 7 ]	BRISQUE [ 10 ]	NIMA [ 19 ]	PSNR	PSNR-HVS-M [ 4 ]	PSNR-HMA [ 20 ]	SI-PSNR	SI-SSIM
	PLCC	0.885	0.921	0.791	0.909	0.462	0.568	0.135	0.876	0.873	0.875	0.905	0.886
	KRCC	0.702	0.741	0.600	0.706	0.320	0.405	0.098	0.696	0.685	0.680	0.724	0.672
KADID-10K [ 18 ]	SROCC	0.887	0.915	0.794	0.893	0.461	0.582	0.119	0.877	0.871	0.866	0.901	0.871
	PLCC	0.912	0.855	0.720	0.887	0.536	0.624	0.315	0.720	0.761	0.702	0.857	0.910
	KRCC	0.753	0.686	0.545	0.712	0.381	0.432	0.146	0.554	0.589	0.540	0.681	0.758
Our Dataset	SROCC	0.920	0.870	0.728	0.900	0.519	0.612	0.163	0.740	0.783	0.726	0.869	0.923

TABLE I : Correlation between IQA metrics and DMOS over two separate datasets . The columns highlighted in grey are NR-IQA. The best and second best performing metrics are highlighted in orange and blue respectively. Our proposed metrics are in italics, bold and underlined (cf. last two columns). Our proposed SI-PSNR produces the best correlation in comparison to all other PSNR variants.

Image Quality Assessment

Image Quality Assessment measures perceived image quality, distortion, and usefulness with computational metrics and human-aligned evaluation.

See all 174 papers

Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions
May 4, 2026Fadeel Sher Khan, Long N. Le, Abhinau K. Venkataramanan +2Image Quality Assessment
The University of Texas at Austin Austin, TX, USA · Samsung Research America Plano, TX, USA
DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training
Oct 8, 2026Jaewan Ko, Janghoon ChoiAdaptive Loss Weighting Image Restoration
Major in Data Science Convergence, Graduate School of Data Science Kyungpook National University, Daegu, Republic of Korea
From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment
Sep 8, 2026Aoting Zhang, Mingze Gao, Dongbao Yang +5Image Quality Assessment
IIE, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Xiaohongshu Inc. +1

May 4, 2026J/K move · Enter open · S save

Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions

Fadeel Sher Khan, Long N. Le, Abhinau K. Venkataramanan, Seok-Jun Lee+1

The University of Texas at Austin Austin, TX, USA · Samsung Research America Plano, TX, USA

Image Quality Assessment

Open paper AskPDF arXiv

Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable, localized feedback on specific image distortions. We overcome these limitations by shifting from absolute quality prediction to a relational and directional assessment. Our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores.

Abstract

Image Quality Assessment

Explore similar work

Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions

DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training

From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment