Direction-aware Spatial Context Features for Shadow Detection and Removal

TL;DR

This paper introduces a direction-aware spatial context neural network for improved shadow detection and removal, leveraging a novel attention mechanism to better understand global image semantics.

Contribution

The paper proposes a new direction-aware attention mechanism within a spatial RNN, integrated into a CNN, for enhanced shadow detection and removal.

Findings

Outperforms state-of-the-art methods in shadow detection

Achieves superior results in shadow removal tasks

Demonstrates effective handling of color and luminosity inconsistencies

Abstract

Shadow detection and shadow removal are fundamental and challenging tasks, requiring an understanding of the global image semantics. This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting and removing shadows. This design is developed into the DSC module and embedded in a convolutional neural network (CNN) to learn the DSC features at different levels. Moreover, we design a weighted cross entropy loss to make effective the training for shadow detection and further adopt the network for shadow removal by using a Euclidean loss function and formulating a color transfer function to address the color and luminosity inconsistencies in the training pairs. We employed two shadow detection benchmark datasets and two shadow removal benchmark datasets, and performed various experiments to evaluate our method. Experimental results show that our method performs favorably against the state-of-the-art methods for both shadow detection and shadow removal.