Geometry-Informed Material Recognition

TL;DR

This paper explores how combining 3D geometry data with 2D image features enhances material recognition accuracy, introducing a new dataset and demonstrating improved classification across various scales and perspectives.

Contribution

It introduces GeoMat, a novel dataset with synchronized image and geometry data, and demonstrates the benefit of integrating 3D geometry with 2D features for material classification.

Findings

Using 2D and 3D features jointly improves accuracy.

Geometry information enhances classification across scales.

The dataset enables large-scale scene analysis.

Abstract

Our goal is to recognize material categories using images and geometry information. In many applications, such as construction management, coarse geometry information is available. We investigate how 3D geometry (surface normals, camera intrinsic and extrinsic parameters) can be used with 2D features (texture and color) to improve material classification. We introduce a new dataset, GeoMat, which is the first to provide both image and geometry data in the form of: (i) training and testing patches that were extracted at different scales and perspectives from real world examples of each material category, and (ii) a large scale construction site scene that includes 160 images and over 800,000 hand labeled 3D points. Our results show that using 2D and 3D features both jointly and independently to model materials improves classification accuracy across multiple scales and viewing directions for both material patches and images of a large scale construction site scene.