LIGHTS: LIGHT Specularity Dataset for specular detection in Multi-view

TL;DR

The paper introduces LIGHTS, a high-quality multi-view dataset for specular highlight detection, and proposes a simple, efficient method that outperforms prior approaches on this dataset.

Contribution

It provides a novel physically-based rendered dataset for specular detection and a simple aggregation method that surpasses previous techniques in accuracy and efficiency.

Findings

The LIGHTS dataset contains 2,603 views across 18 scenes.

The proposed method outperforms prior work by 3.6%.

The method is two orders of magnitude faster than previous approaches.

Abstract

Specular highlights are commonplace in images, however, methods for detecting them and in turn removing the phenomenon are particularly challenging. A reason for this, is due to the difficulty of creating a dataset for training or evaluation, as in the real-world we lack the necessary control over the environment. Therefore, we propose a novel physically-based rendered LIGHT Specularity (LIGHTS) Dataset for the evaluation of the specular highlight detection task. Our dataset consists of 18 high quality architectural scenes, where each scene is rendered with multiple views. In total we have 2,603 views with an average of 145 views per scene. Additionally we propose a simple aggregation based method for specular highlight detection that outperforms prior work by 3.6% in two orders of magnitude less time on our dataset.