# A 4D Light-Field Dataset and CNN Architectures for Material Recognition

Source: [A 4D Light-Field Dataset and CNN Architectures for Material Recognition](<https://www.sota2.com/research/paper/68fa62ba1e209131ce9fae88>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:25:18.953Z

Authors: Ting-Chun Wang, Jun-Yan Zhu, Ebi Hiroaki, Manmohan Chandraker, Alexei A. Efros, Ravi Ramamoorthi

Published: 2016-08-24T23:30:22.000Z

## Abstract

We introduce a new light-field dataset of materials, and take advantage of the recent success of deep learning to perform material recognition on the 4D light-field. Our dataset contains 12 material categories, each with 100 images taken with a Lytro Illum, from which we extract about 30,000 patches in total. To the best of our knowledge, this is the first mid-size dataset for light-field images. Our main goal is to investigate whether the additional information in a light-field (such as multiple sub-aperture views and view-dependent reflectance effects) can aid material recognition. Since recognition networks have not been trained on 4D images before, we propose and compare several novel CNN architectures to train on light-field images. In our experiments, the best performing CNN architecture achieves a 7% boost compared with 2D image classification (70% to 77%). These results constitute important baselines that can spur further research in the use of CNNs for light-field applications. Upon publication, our dataset also enables other novel applications of light-fields, including object detection, image segmentation and view interpolation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1608.06985>)

[PDF](<https://arxiv.org/pdf/1608.06985.pdf>)
