Towards Top-Down Just Noticeable Difference Estimation of Natural Images

TL;DR

This paper introduces a top-down approach for estimating the just noticeable difference (JND) in natural images by predicting a critical perceptual lossless image and deriving the JND from their difference, outperforming existing models.

Contribution

A novel top-down JND estimation model that predicts a critical perceptual lossless image and uses its difference from the original for JND estimation, with demonstrated superior performance.

Findings

Outperforms recent JND models in prediction accuracy.

Effectively guides noise injection and image compression.

Comparable to visual difference predictors in distortion detection.

Abstract

Just noticeable difference (JND) of natural images refers to the maximum pixel intensity change magnitude that typical human visual system (HVS) cannot perceive. Existing efforts on JND estimation mainly dedicate to modeling the diverse masking effects in either/both spatial or/and frequency domains, and then fusing them into an overall JND estimate. In this work, we turn to a dramatically different way to address this problem with a top-down design philosophy. Instead of explicitly formulating and fusing different masking effects in a bottom-up way, the proposed JND estimation model dedicates to first predicting a critical perceptual lossless (CPL) counterpart of the original image and then calculating the difference map between the original image and the predicted CPL image as the JND map. We conduct subjective experiments to determine the critical points of 500 images and find that the distribution of cumulative normalized KLT coefficient energy values over all 500 images at these critical points can be well characterized by a Weibull distribution. Given a testing image, its corresponding critical point is determined by a simple weighted average scheme where the weights are determined by a fitted Weibull distribution function. The performance of the proposed JND model is evaluated explicitly with direct JND prediction and implicitly with two applications including JND-guided noise injection and JND-guided image compression. Experimental results have demonstrated that our proposed JND model can achieve better performance than several latest JND models. In addition, we also compare the proposed JND model with existing visual difference predicator (VDP) metrics in terms of the capability in distortion detection and discrimination. The results indicate that our JND model also has a good performance in this task.