Saved in:
Bibliographic Details
Main Authors: Beveridge, Matthew, Nayar, Shree K.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.22911
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915562578247680
author Beveridge, Matthew
Nayar, Shree K.
author_facet Beveridge, Matthew
Nayar, Shree K.
contents We introduce a taxonomy of materials for hierarchical recognition from local appearance. Our taxonomy is motivated by vision applications and is arranged according to the physical traits of materials. We contribute a diverse, in-the-wild dataset with images and depth maps of the taxonomy classes. Utilizing the taxonomy and dataset, we present a method for hierarchical material recognition based on graph attention networks. Our model leverages the taxonomic proximity between classes and achieves state-of-the-art performance. We demonstrate the model's potential to generalize to adverse, real-world imaging conditions, and that novel views rendered using the depth maps can enhance this capability. Finally, we show the model's capacity to rapidly learn new materials in a few-shot learning setting.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22911
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Material Recognition from Local Appearance
Beveridge, Matthew
Nayar, Shree K.
Computer Vision and Pattern Recognition
We introduce a taxonomy of materials for hierarchical recognition from local appearance. Our taxonomy is motivated by vision applications and is arranged according to the physical traits of materials. We contribute a diverse, in-the-wild dataset with images and depth maps of the taxonomy classes. Utilizing the taxonomy and dataset, we present a method for hierarchical material recognition based on graph attention networks. Our model leverages the taxonomic proximity between classes and achieves state-of-the-art performance. We demonstrate the model's potential to generalize to adverse, real-world imaging conditions, and that novel views rendered using the depth maps can enhance this capability. Finally, we show the model's capacity to rapidly learn new materials in a few-shot learning setting.
title Hierarchical Material Recognition from Local Appearance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.22911