Instance Shadow Detection

@article{Wang2020InstanceSD,
  title={Instance Shadow Detection},
  author={Tianyu Wang and Xiaowei Hu and Qiong Wang and Pheng-Ann Heng and Chi-Wing Fu},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={1877-1886}
}
Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the… Expand
Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
TLDR
This work 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. Expand
From Shadow Generation to Shadow Removal
TLDR
A new G2R-ShadowNet is proposed which leverages shadow generation for weakly-supervised shadow removal by only using a set of shadow images and their corresponding shadow masks for training and achieves competitive performances against the current state of the arts and outperforms Le and Samaras' patch-based shadow-removal method. Expand
Learning from Synthetic Shadows for Shadow Detection and Removal
TLDR
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. Expand
From Shadow Segmentation to Shadow Removal
TLDR
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. Expand
No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry
TLDR
A deep learning pipeline for removing a shadow along with its caster is introduced, leveraging rough scene models in order to remove a wide variety of shadows from surfaces with a wide range of textures. Expand
Pyramid Spatial Context Features for Salient Object Detection
  • H. Li
  • Computer Science
  • IEEE Access
  • 2020
TLDR
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. Expand
Toward Mass Video Data Analysis: Interactive and Immersive 4D Scene Reconstruction
TLDR
The VICTORIA Interactive 4D Scene Reconstruction and Analysis Framework is presented, an approach for the visual consolidation of heterogeneous video and image data in a 3D reconstruction of the corresponding environment and allows the user to immerse themselves in the analysis by entering the scenario in virtual reality. Expand
Omnimatte: Associating Objects and Their Effects in Video
TLDR
This work estimates an omnimatte for each subject—an alpha matte and color image that includes the subject along with all its related time-varying scene elements that produces omnimattes automatically for arbitrary objects and a variety of effects. Expand
Single-Stage Instance Shadow Detection With Bidirectional Relation Learning
TLDR
A new single-stage fullyconvolutional 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 clearly outperforms the state-of-the-art method for instance shadow detection. Expand
Learning to detect soft shadow from limited data
TLDR
A novel soft shadow detection method (namely Soft-DA) based on adversarial learning and domain adaptation scheme that can achieve superior performance to state of the arts and introduce a novel detector separation strategy to tackle the intention difference issue. Expand
...
1
2
...

References

SHOWING 1-10 OF 59 REFERENCES
MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
TLDR
This work presents a model, called MaskLab, which produces three outputs: box detection, semantic segmentation, and direction prediction, which is evaluated on the COCO instance segmentation benchmark and shows comparable performance with other state-of-art models. Expand
Boundary-Aware Instance Segmentation
TLDR
This paper introduces a novel object segment representation based on the distance transform of the object masks, and designs an object mask network (OMN) with a new residual-deconvolution architecture that infers such a representation and decodes it into the final binary object mask. Expand
Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
TLDR
This work 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. Expand
Single-image shadow detection and removal using paired regions
TLDR
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. Expand
Pixelwise Instance Segmentation with a Dynamically Instantiated Network
TLDR
An Instance Segmentation system that produces a segmentation map where each pixel is assigned an object class and instance identity label, and far more precise segmentations are achieved, as shown by substantial improvements at high APr thresholds. Expand
Distraction-Aware Shadow Detection
TLDR
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. Expand
Automatic Feature Learning for Robust Shadow Detection
TLDR
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. Expand
Automatic Shadow Detection and Removal from a Single Image
TLDR
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. Expand
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of sceneExpand
Large Scale Shadow Annotation and Detection Using Lazy Annotation and Stacked CNNs
TLDR
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. Expand
...
1
2
3
4
5
...