Shadow Removal

50 papers with code • 3 benchmarks • 6 datasets

Remove shadow from background

Most implemented papers

Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data

xw-hu/Mask-ShadowGAN ICCV 2019

This paper presents a new method for shadow removal using unpaired data, enabling us to avoid tedious annotations and obtain more diverse training samples.

Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN

vinthony/ghost-free-shadow-removal 20 Nov 2019

With the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images.

Shadow Removal via Shadow Image Decomposition

lmhieu612/SID ICCV 2019

Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7. 4.

RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal

zhling2020/RIS-GAN 20 Nov 2019

To our best knowledge, we are the first one to explore residual and illumination for shadow removal.

Direction-aware Spatial Context Features for Shadow Detection and Removal

xw-hu/DSC 12 May 2018

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.

Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal

seungjun45/Water-Filling 22 Apr 2019

In this paper, we propose a novel algorithm to rectify illumination of the digitized documents by eliminating shading artifacts.

BEDSR-Net: A Deep Shadow Removal Network From a Single Document Image

IsHYuhi/BEDSR-Net_A_Deep_Shadow_Removal_Network_from_a_Single_Document_Image CVPR 2020

For taking advantage of specific properties of document images, a background estimation module is designed for extracting the global background color of the document.

Physics-based Shadow Image Decomposition for Shadow Removal

cvlab-stonybrook/SID 23 Dec 2020

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.

Auto-Exposure Fusion for Single-Image Shadow Removal

tsingqguo/exposure-fusion-shadow-removal CVPR 2021

We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods.