Shadow Detection

37 papers with code • 1 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

CloudS2Mask: A novel deep learning approach for improved cloud and cloud shadow masking in Sentinel-2 imagery

DPIRD-DMA/CloudS2Mask Remote Sensing of Environment 2024

Precise and efficient cloud and cloud shadow masking methods are required for the automated use of this data.

7
15 May 2024

NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI

Yuki-11/NTIRE2023_ShadowRemoval_IIM_TTI 13 Mar 2024

In this paper, we analyze and discuss ShadowFormer in preparation for the NTIRE2023 Shadow Removal Challenge [1], implementing five key improvements: image alignment, the introduction of a perceptual quality loss function, the semi-automatic annotation for shadow detection, joint learning of shadow detection and removal, and the introduction of new data augmentation technique "CutShadow" for shadow removal.

2
13 Mar 2024

Delving into Dark Regions for Robust Shadow Detection

guanhuankang/shadowdetection2021 21 Feb 2024

Our key insight to this problem is that existing methods typically learn discriminative shadow features from the whole image globally, covering the full range of intensity values, and may not learn the subtle differences between shadow and non-shadow pixels in dark regions.

2
21 Feb 2024

AdapterShadow: Adapting Segment Anything Model for Shadow Detection

leipingjie/adaptershadow 15 Nov 2023

To adapt SAM for shadow images, trainable adapters are inserted into the frozen image encoder of SAM, since the training of the full SAM model is both time and memory consuming.

0
15 Nov 2023

SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels

cralence/silt ICCV 2023

Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data.

8
23 Aug 2023

SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection

rmcong/sddnet_acmmm23 17 Aug 2023

Despite significant progress in shadow detection, current methods still struggle with the adverse impact of background color, which may lead to errors when shadows are present on complex backgrounds.

6
17 Aug 2023

SAM-helps-Shadow:When Segment Anything Model meet shadow removal

zhangbaijin/sam-helps-shadow 1 Jun 2023

The challenges surrounding the application of image shadow removal to real-world images and not just constrained datasets like ISTD/SRD have highlighted an urgent need for zero-shot learning in this field.

10
01 Jun 2023

Explicit Visual Prompting for Universal Foreground Segmentations

nifangbaage/explicit-visual-prompt 29 May 2023

We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP).

157
29 May 2023

Detect Any Shadow: Segment Anything for Video Shadow Detection

harrytea/detect-anyshadow 26 May 2023

Segment anything model (SAM) has achieved great success in the field of natural image segmentation.

36
26 May 2023

When SAM Meets Shadow Detection

leipingjie/samshadow 19 May 2023

As a promptable generic object segmentation model, segment anything model (SAM) has recently attracted significant attention, and also demonstrates its powerful performance.

10
19 May 2023