# Fine-Context Shadow Detection using Shadow Removal

arXiv: https://arxiv.org/abs/2109.09609 · HTML: https://mlsanity.com/paper/2109.09609/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 51 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 16 of 16)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Reverse Attention for Salient Object Detection](https://mlsanity.com/paper/1807.09940/) (2018)
- [Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN](https://mlsanity.com/paper/1911.08718/) (2019)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Rendering Synthetic Objects into Legacy Photographs](https://mlsanity.com/paper/1912.11565/) (2019)
- [Direction-aware Spatial Context Features for Shadow Detection and Removal](https://mlsanity.com/paper/1805.04635/) (2018)
- [KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations](https://mlsanity.com/paper/2006.04878/) (2020)
- [A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation](https://mlsanity.com/paper/1712.01361/) (2017)
- [KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation](https://mlsanity.com/paper/2010.01663/) (2020)
- [Triple-cooperative Video Shadow Detection](https://mlsanity.com/paper/2103.06533/) (2021)
- [Exploring Overcomplete Representations for Single Image Deraining using CNNs](https://mlsanity.com/paper/2010.10661/) (2020)
- [Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network](https://mlsanity.com/paper/1709.09283/) (2017)
- [Self-Supervised Shadow Removal](https://mlsanity.com/paper/2010.11619/) (2020)

## Built on by (most cited first, 9 of 9)

- [SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection](https://mlsanity.com/paper/2308.08935/) (2023)
- [Test-Time Intensity Consistency Adaptation for Shadow Detection](https://mlsanity.com/paper/2410.07695/) (2024)
- [Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era](https://mlsanity.com/paper/2409.02108/) (2024)
- [When SAM Meets Shadow Detection](https://mlsanity.com/paper/2305.11513/) (2023)
- [AdapterShadow: Adapting Segment Anything Model for Shadow Detection](https://mlsanity.com/paper/2311.08891/) (2023)
- [TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks](https://mlsanity.com/paper/2408.01835/) (2024)
- [SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection](https://mlsanity.com/paper/2408.03521/) (2024)
- [RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification](https://mlsanity.com/paper/2408.17143/) (2024)
- [Revisiting Shadow Detection from a Vision-Language Perspective](https://mlsanity.com/paper/2605.11771/) (2026)

## Abstract (arXiv)

Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges. In this work, we attempt to address this problem on two fronts. First, we propose a Fine Context-aware Shadow Detection Network (FCSD-Net), where we constraint the receptive field size and focus on low-level features to learn fine context features better. Second, we propose a new learning strategy, called Restore to Detect (R2D), where we show that when a deep neural network is trained for restoration (shadow removal), it learns meaningful features to delineate the shadow masks as well. To make use of this complementary nature of shadow detection and removal tasks, we train an auxiliary network for shadow removal and propose a complementary feature learning block (CFL) to learn and fuse meaningful features from shadow removal network to the shadow detection network. We train the proposed network, FCSD-Net, using the R2D learning strategy across multiple datasets. Experimental results on three public shadow detection datasets (ISTD, SBU and UCF) show that our method improves the shadow detection performance while being able to detect fine context better compared to the other recent methods.