DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network

  title={DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network},
  author={Yeying Jin and Aashish Sharma and Robby T. Tan},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
Shadow removal from a single image is generally still an open problem. Most existing learning-based methods use supervised learning and require a large number of paired images (shadow and corresponding non-shadow images) for training. A recent unsupervised method, Mask-ShadowGAN [13], addresses this limitation. However, it requires a binary mask to represent shadow regions, making it inapplicable to soft shadows. To address the problem, in this paper, we propose an unsupervised domain… 

Style-Guided Shadow Removal

This work proposes a style-guided shadow removal network (SG-ShadowNet) for better image-style consistency after shadow removal, which outperforms all the existing competitive models and achieves a new state-of-the-art performance on ISTD+, SRD, and Video Shadow Removal benchmark datasets.

CNSNet: A Cleanness-Navigated-Shadow Network for Shadow Removal

A novel cleanness-navigated-shadow network (CNSNet) with a shadow-oriented adaptive normalization (SOAN) module and ashadow-aware aggregation with transformer (SAAT) module based on the shadow mask, which achieves superior de-shadowing performance.

Bijective Mapping Network for Shadow Removal

A new Bijective Mapping Network (BMNet), which couples the learning procedures of shadow removal and shadow generation in a unified parameter-shared framework and outperforms the state-of-the-art method in de-shadowing performance, while only using its 0.25% network parameters and 6.

CRFormer: A Cross-Region Transformer for Shadow Removal

A novel cross-region transformer, namely CRFormer, is proposed for shadow removal which differs from existing transformers by only considering the pixel interactions from the non-shadow region to the shadow region without splitting images into patches.

Depth-Aware Shadow Removal

This paper proposes a novel end-to-end depth-aware shadow removal method without using depth images, which estimates depth information from RGB images and leverages the depth feature as guidance to enhance shadow removal and refinement.

LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal

A novel lightweight deep neural network that processes shadow images in the LAB color space that well outperforms state-of-the-art methods and its parameters and computational costs are reduced by several orders of magni-tude.

Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning

Estimating reflectance layer from a single image is a challenging task. It becomes more challenging when the input image contains shadows or specular highlights, which often render an inaccurate

TAPE: Task-Agnostic Prior Embedding for Image Restoration

A novel approach that embeds a task-agnostic prior into a transformer and shows the ability of disentangling generalized image priors from degraded images, which enjoys favorable transfer ability to unknown downstream tasks.

Shadow Removal for Documents with Reflective Textured Surface

A shadow removal mechanism based on Dual Hierarchical Aggregation Network (DHAN) and VGG-19 (Convolutional network by Visual Geometry Group) object detection deep learning model is proposed for the NIC dataset, which is a relatively new target domain.

Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression

. Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This



Shadow Removal via Shadow Image Decomposition

  • Hieu M. LeD. Samaras
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
A novel deep learning method is proposed for shadow removal that uses 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.

From Shadow Segmentation to Shadow Removal

This work proposes a shadow removal method that can be trained using only shadow and non-shadow patches cropped from the shadow images themselves, trained via an adversarial framework, following a physical model of shadow formation.

Automatic Shadow Detection and Removal from a Single Image

A framework to automatically detect and remove shadows in real world scenes from a single image using multiple convolutional deep neural networks (ConvNets) based on a novel model which accurately models the shadow generation process in the umbra and penumbra regions.

Single-image shadow detection and removal using paired regions

This paper addressed the problem of shadow detection and removal from single images of natural scenes by employing a region based approach, and created a new dataset with shadow-free ground truth images, which provides a quantitative basis for evaluating shadow removal.

Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data

Mask-ShadowGAN is a new deep framework that automatically learns to produce a shadow mask from the input shadow image and then takes the mask to guide the shadow generation via re-formulated cycle-consistency constraints, to maximize the overall performance.

Direction-Aware Spatial Context Features for Shadow Detection and Removal

This paper designs 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.

Paired Regions for Shadow Detection and Removal

This paper addresses the problem of shadow detection and removal from single images of natural scenes by employing a region-based approach, and predicts relative illumination conditions between segmented regions from their appearances and performs pairwise classification based on such information.

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

A shadow matting generative adversarial network (SMGAN) is designed to synthesize realistic shadow mattings from a given shadow mask and shadow-free image to outperforms other state-of-the-art methods by a large margin.

Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal

This paper presents a multi-task perspective, which is not embraced by any existing work, to jointly learn both detection and removal in an end-to-end fashion that aims at enjoying the mutually improved benefits from each other.

Interactive Shadow Removal and Ground Truth for Variable Scene Categories

This work presents the first reliable, validated and multi-scene category ground truth for shadow removal algorithms which overcomes limitations in existing data sets -- such as inconsistencies between shadow and shadow-free images and limited variations of shadows.