首个直接在BRDF空间评估材质质量的神经网络指标，更贴近人眼感知。
A Neural Quality Metric for BRDF Models
- 用神经网络直接在BRDF空间计算感知质量，无需渲染过程。
- 相比传统方法，与人类判断的相关性显著提升，达0.87以上。
- 适合需要真实感材质评估的研究者，尤其适用于渲染质量验证。
准确评估双向反射分布函数（BRDF）模型的质量对于实现逼真渲染至关重要。传统基于BRDF空间的度量方法常采用数值误差指标，难以捕捉渲染图像中的人眼感知差异。本文提出首个基于感知的神经质量度量，直接在BRDF空间运行，无需渲染即可完成评估。该度量以紧凑的多层感知机（MLP）实现，训练数据来自实测BRDF与合成数据，并使用经过感知验证的图像空间度量进行标注。网络输入一对参考与近似BRDF样本，输出其在刚刚可察觉差异（JOD）意义上的感知质量评分。实验表明，该神经度量与人类判断的相关性显著优于现有BRDF空间度量。尽管其作为BRDF拟合损失函数的效果有限，但为BRDF模型评估提供了感知可靠的新工具。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。