Revisiting Shadow Detection: A New Benchmark Dataset for Complex World

  title={Revisiting Shadow Detection: A New Benchmark Dataset for Complex World},
  author={Xiaowei Hu and Tianyu Wang and Chi-Wing Fu and Yitong Jiang and Qiong Wang and Pheng-Ann Heng},
  journal={IEEE Transactions on Image Processing},
Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers… 
Learning From Synthetic Shadows for Shadow Detection and Removal
It is demonstrated that shadow removal models trained on SynShadow perform well in removing shadows with diverse shapes and intensities on some challenging benchmarks, and it is shown that merely fine-tuning from a SynShadow-pre-trained model improves existing shadow detection and removal models.
Instance Shadow Detection
LISA is designed, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction, and demonstrates its applicability on light direction estimation and photo editing.
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.
Pyramid Spatial Context Features for Salient Object Detection
  • H. Li
  • Computer Science
    IEEE Access
  • 2020
A novel deep neural network design for salient object detection by formulating a pyramid spatial context module, PSC module for short, to capture the spatial context information at multiple scales by inserting this module in a deep network, namely PSCNet.
Shadow Detection via Predicting the Confidence Maps of Shadow Detection Methods
To measure the shadow detection confidence characteristics of an image, a novel relative confidence map prediction network (RCMPNet) is proposed and experimental results show that the proposed method outperforms multiple state-of-the-art shadow detection methods on four shadow detection benchmark datasets.
Learning-Based Shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds
Shadows, motion parallax, and occlusions pose significant challenges to vision tasks in wide area motion imagery (WAMI) including object identification and tracking. Although there are many
Robust Shadow Detection by Exploring Effective Shadow Contexts
  • Xianyong Fang, Xiaohao He, Linbo Wang, Jianbing Shen
  • Computer Science
    ACM Multimedia
  • 2021
This paper proposes a novel encoder-decoder style of shadow detection method where ECA acts as the main building block of the encoder to extract strong feature representations and the guidance to the classification process of the decoder.
Temporal Feature Warping for Video Shadow Detection
This paper uses an optical flow based warping module to align and then combine features between frames to retrieve information from neighboring frames including both local details and high-level semantic information and shows results that outperforms the state-of-the-art video shadow detection method.
Light-weight shadow detection via GCN-based annotation strategy and knowledge distillation
  • Wen Wu, Kai Zhou, Xiao-Diao Chen, J. Yong
  • Computer Vision and Image Understanding
  • 2021
Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
This paper presents a new single-stage fully-convolutional network architecture with a bidirectional relation learning module to directly learn the relations of shadow and object instances in an end-to-end manner and evaluates the method on the benchmark dataset for instance shadow detection.


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.
Shadow Detection and Removal in Real Images: A Survey
Abstract. Shadow detection and removal in real scene images is always a challenging but yet intriguing problem. In contrast with the rapidly expanding and continuous interests on this area, the
Automatic Feature Learning for Robust Shadow Detection
This work presents a practical framework to automatically detect shadows in real world scenes from a single photograph using multiple convolutional deep neural networks (ConvNets) and learns features at the super-pixel level and along the object boundaries.
Large-Scale Training of Shadow Detectors with Noisily-Annotated Shadow Examples
A semantic-aware patch level Convolutional Neural Network architecture that efficiently trains on patch level shadow examples while incorporating image level semantic information means that the detected shadow patches are refined based on image semantics.
Shadow optimization from structured deep edge detection
  • Li Shen, T. Chua, K. Leman
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
This paper presents a novel learning-based framework for shadow region recovery from a single image by using a structured CNN learning framework, and proposes and forms shadow/bright measure to model complex interactions among image regions.
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.
Distraction-Aware Shadow Detection
Experimental results demonstrate that the proposed Distraction-aware Shadow Detection Network can boost shadow detection performance, by effectively suppressing the detection of false positives and false negatives, achieving state-of-the-art results.
Learning to recognize shadows in monochromatic natural images
Results show shadowed areas of an image can be identified using proposed monochromatic cues, which are used to train a classifier from boosting a decision tree and integrated into a Conditional random Field, which can enforce local consistency over pixel labels.
Large Scale Shadow Annotation and Detection Using Lazy Annotation and Stacked CNNs
This paper proposes a stacked Convolutional Neural Network architecture that efficiently trains on patch level shadow examples while incorporating image level semantic information, which means that the detected shadow patches are refined based on image semantics.
Detecting Ground Shadows in Outdoor Consumer Photographs
The key hypothesis is that the types of materials constituting the ground in outdoor scenes is relatively limited, most commonly including asphalt, brick, stone, mud, grass, concrete, etc, so the appearances of shadows on the ground are not as widely varying as general shadows and thus, can be learned from a labelled set of images.