ISTD

Dataset Information
Modalities
Images
Introduced
2018
License
Custom (research-only, non-commercial)
Homepage
Official Website
Contents

Overview

The Image Shadow Triplets dataset (ISTD) is a dataset for shadow understanding that contains 1870 image triplets of shadow image, shadow mask, and shadow-free image.

Source: ST-CGAN: "Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal"
Image Source: Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal

Variants: ISTD

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Shadow Removal ShadowRefiner ShadowRefiner: Towards Mask-free Shadow Removal … 2024-04-18
Shadow Removal Resfusion Resfusion: Denoising Diffusion Probabilistic Models … 2023-11-25
Shadow Removal ShadowFormer ShadowFormer: Global Context Helps Image … 2023-02-03
Shadow Removal DC-ShadowNet DC-ShadowNet: Single-Image Hard and Soft … 2022-07-21
Shadow Removal Zhang et al. SpA-Former: Transformer image shadow detection … 2022-06-22
Shadow Removal DHAN+DA Towards Ghost-free Shadow Removal via … 2019-11-20
Shadow Removal DHAN Towards Ghost-free Shadow Removal via … 2019-11-20
RGB Salient Object Detection CPD Cascaded Partial Decoder for Fast … 2019-04-18
Shadow Removal DSC Direction-aware Spatial Context Features for … 2018-05-12
RGB Salient Object Detection DSC Direction-aware Spatial Context Features for … 2017-12-12
RGB Salient Object Detection JDR Stacked Conditional Generative Adversarial Networks … 2017-12-07
Shadow Removal ST-CGAN Stacked Conditional Generative Adversarial Networks … 2017-12-07
RGB Salient Object Detection DSS Deeply supervised salient object detection … 2016-11-15

Research Papers

Recent papers with results on this dataset:

External Links: