A Neural Quality Metric for BRDF Models

TL;DR

This paper introduces a neural, perceptually informed quality metric for BRDF models that directly assesses perceptual differences without rendering, outperforming traditional numerical metrics in correlating with human judgments.

Contribution

The paper presents the first neural perceptual metric for BRDF evaluation that operates directly in BRDF space, trained on perceptually validated data, and correlates better with human perception.

Findings

Neural metric outperforms existing BRDF-space metrics in correlation with human judgments.

The metric operates without rendering, enabling efficient perceptual evaluation.

Limited effectiveness as a loss function for BRDF fitting.

Abstract

Accurately evaluating the quality of bidirectional reflectance distribution function (BRDF) models is essential for photo-realistic rendering. Traditional BRDF-space metrics often employ numerical error measures that fail to capture perceptual differences evident in rendered images. In this paper, we introduce the first perceptually informed neural quality metric for BRDF evaluation that operates directly in BRDF space, eliminating the need for rendering during quality assessment. Our metric is implemented as a compact multi-layer perceptron (MLP), trained on a dataset of measured BRDFs supplemented with synthetically generated data and labelled using a perceptually validated image-space metric. The network takes as input paired samples of reference and approximated BRDFs and predicts their perceptual quality in terms of just-objectionable-difference (JOD) scores. We show that our neural metric achieves significantly higher correlation with human judgments than existing BRDF-space metrics. While its performance as a loss function for BRDF fitting remains limited, the proposed metric offers a perceptually grounded alternative for evaluating BRDF models.