Shadow Optimization from Structured Deep Edge Detection

Abstract

Local structures of shadow boundaries as well as complex interactions of image regions remain largely unexploited by previous shadow detection approaches. In this paper, we present a novel learning-based framework for shadow region recovery from a single image. We exploit the local structures of shadow edges by using a structured CNN learning framework. We show that using the structured label information in the classification can improve the local consistency of the results and avoid spurious labelling. We further propose and formulate a shadow/bright measure to model the complex interactions among image regions. The shadow and bright measures of each patch are computed from the shadow edges detected in the image. Using the global interaction constraints on patches, we formulate a least-square optimization problem for shadow recovery that can be solved efficiently. Our shadow recovery method achieves state-of-the-art results on the major shadow benchmark databases collected under various conditions.

8 pages. CVPR 2015

Cited by in corpus (5)

• Direction-aware Spatial Context Features for Shadow Detection
• Makeup like a superstar: Deep Localized Makeup Transfer Network
• Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
• Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
• Fractal Dimension Invariant Filtering and Its CNN-based Implementation