The joint role of geometry and illumination on material recognition

TL;DR

This study investigates how geometry and illumination influence human material recognition, revealing complex interactions and demonstrating that deep neural networks can model human-like recognition processes.

Contribution

It provides a comprehensive analysis of the effects of geometry and illumination on material recognition and compares human performance with deep neural network models.

Findings

Significant interactions between geometry and illumination affect recognition.

Simple image statistics do not correlate with human performance.

Deep neural networks can classify materials effectively, resembling human high-level processing.

Abstract

Observing and recognizing materials is a fundamental part of our daily life. Under typical viewing conditions, we are capable of effortlessly identifying the objects that surround us and recognizing the materials they are made of. Nevertheless, understanding the underlying perceptual processes that take place to accurately discern the visual properties of an object is a long-standing problem. In this work, we perform a comprehensive and systematic analysis of how the interplay of geometry, illumination, and their spatial frequencies affects human performance on material recognition tasks. We carry out large-scale behavioral experiments where participants are asked to recognize different reference materials among a pool of candidate samples. In the different experiments, we carefully sample the information in the frequency domain of the stimuli. From our analysis, we find significant first-order interactions between the geometry and the illumination, of both the reference and the candidates. In addition, we observe that simple image statistics and higher-order image histograms do not correlate with human performance. Therefore, we perform a high-level comparison of highly non-linear statistics by training a deep neural network on material recognition tasks. Our results show that such models can accurately classify materials, which suggests that they are capable of defining a meaningful representation of material appearance from labeled proximal image data. Last, we find preliminary evidence that these highly non-linear models and humans may use similar high-level factors for material recognition tasks.