About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

Direction-aware Spatial Context Features for Shadow Detection and Removal

12 May 2018xw-hu/DSC

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.

SHADOW DETECTION AND REMOVAL SHADOW REMOVAL

Direction-aware Spatial Context Features for Shadow Detection

CVPR 2018 xw-hu/DSC

To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN.

DETECTING SHADOWS SHADOW DETECTION

Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection

ECCV 2018 zijundeng/BDRAR

Second, we develop a bidirectional feature pyramid network (BFPN) to aggregate shadow contexts spanned across different CNN layers by deploying two series of RAR modules in the network to iteratively combine and refine context features: one series to refine context features from deep to shallow layers, and another series from shallow to deep layers.

SHADOW DETECTION

Instance Shadow Detection

CVPR 2020 stevewongv/InstanceShadowDetection

Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results.

SHADOW DETECTION

A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection

CVPR 2020 eraserNut/MTMT

To boost the shadow detection performance, this paper presents a multi-task mean teacher model for semi-supervised shadow detection by leveraging unlabeled data and exploring the learning of multiple information of shadows simultaneously.

 Ranked #1 on Shadow Detection on SBU (using extra training data)

SHADOW DETECTION

Learning from Synthetic Shadows for Shadow Detection and Removal

5 Jan 2021naoto0804/SynShadow

To overcome this challenge, we present SynShadow, a novel large-scale synthetic shadow/shadow-free/matte image triplets dataset and a pipeline to synthesize it.

SHADOW DETECTION AND REMOVAL SHADOW REMOVAL

Conditional GANs for Multi-Illuminant Color Constancy: Revolution or Yet Another Approach?

15 Nov 2018acecreamu/angularGAN

Non-uniform and multi-illuminant color constancy are important tasks, the solution of which will allow to discard information about lighting conditions in the image.

COLOR CONSTANCY SHADOW DETECTION AND REMOVAL SHADOW REMOVAL

Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network

26 Sep 2017sepidehhosseinzadeh/Fast-Shadow-Detection

In recent years, various shadow detection methods from a single image have been proposed and used in vision systems; however, most of them are not appropriate for the robotic applications due to the expensive time complexity.

SHADOW DETECTION