Shadow Removal via Shadow Image Decomposition

by   Hieu Le, et al.
Stony Brook University

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects on the images. We train and test our framework on the most challenging shadow removal dataset (ISTD). Compared to the state-of-the-art method, our model achieves a 40 terms of root mean square error (RMSE) for the shadow area, reducing RMSE from 13.3 to 7.9. Moreover, we create an augmented ISTD dataset based on an image decomposition system by modifying the shadow parameters to generate new synthetic shadow images. Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7.4.


page 4

page 5

page 6

page 7

page 8


Physics-based Shadow Image Decomposition for Shadow Removal

We propose a novel deep learning method for shadow removal. Inspired by ...

Physically Inspired Dense Fusion Networks for Relighting

Image relighting has emerged as a problem of significant research intere...

From Shadow Segmentation to Shadow Removal

The requirement for paired shadow and shadow-free images limits the size...

A deep learning approach for analyzing the composition of chemometric data

We propose novel deep learning based chemometric data analysis technique...

Learning from Synthetic Shadows for Shadow Detection and Removal

Shadow removal is an essential task in computer vision and computer grap...

P-HGRMS: A Parallel Hypergraph Based Root Mean Square Algorithm for Image Denoising

This paper presents a parallel Salt and Pepper (SP) noise removal algori...

Multiple Linear Regression Haze-removal Model Based on Dark Channel Prior

Dark Channel Prior (DCP) is a widely recognized traditional dehazing alg...

Code Repositories


Learning from Synthetic Shadows for Shadow Detection and Removal [Inoue and Yamasaki, IEEE TCSVT 2020].

view repo


Official implementation for ICCV19 "Shadow Removal via Shadow Image Decomposition"

view repo

Please sign up or login with your details

Forgot password? Click here to reset