Revisiting Shadow Detection: A New Benchmark Dataset for Complex World

TL;DR

This work collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world.

Abstract

Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.

Figures (10)

• Figure 1: Example shadow images and masks in ISTD wang2018stacked, SBU hou2019largevicente2016noisyvicente2016large, and our CUHK-Shadow dataset.
• Figure 2: Example shadow images and shadow masks for categories (i) to (v) in our dataset; see Section \ref{['sec:dataset_construction']} for details.
• Figure 3: Analysis on the shadow area proportion for different datasets. Shadows in the ISTD and SBU datasets have mainly small shadows, while our CUHK-Shadow has more diverse types of shadows with wider ranges of sizes in the shadow images.
• Figure 4: Shadow location distributions. Lighter (darker) colors indicate larger (smaller) chances of having shadows.
• Figure 5: Color contrast distributions of different datasets.