LIGHTS: LIGHT Specularity Dataset for specular detection in Multi-view
This addresses the problem of specular highlight detection for computer vision researchers, providing a controlled dataset and a faster method, though it is incremental in nature.
The paper tackles the challenge of detecting specular highlights in images by proposing the LIGHTS dataset, a novel physically-based rendered dataset with 18 scenes and 2,603 views, and introduces a simple aggregation method that outperforms prior work by 3.6% in significantly less time.
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.