DocDeshadower: Frequency-aware Transformer for Document Shadow Removal
- URL: http://arxiv.org/abs/2307.15318v1
- Date: Fri, 28 Jul 2023 05:35:37 GMT
- Title: DocDeshadower: Frequency-aware Transformer for Document Shadow Removal
- Authors: Shenghong Luo, Ruifeng Xu, Xuhang Chen, Zinuo Li, Chi-Man Pun and
Shuqiang Wang
- Abstract summary: DocDeshadower is a multi-frequency Transformer-based model built on Laplacian Pyramid.
We decompose the shadow image into different frequency bands using Laplacian Pyramid.
Attention-Aggregation Network is designed to remove shadows in the low-frequency part of the image.
Gated Multi-scale Fusion Transformer refines the entire image at a global scale with its large perceptive field.
- Score: 49.107557554811144
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The presence of shadows significantly impacts the visual quality of scanned
documents. However, the existing traditional techniques and deep learning
methods used for shadow removal have several limitations. These methods either
rely heavily on heuristics, resulting in suboptimal performance, or require
large datasets to learn shadow-related features. In this study, we propose the
DocDeshadower, a multi-frequency Transformer-based model built on Laplacian
Pyramid. DocDeshadower is designed to remove shadows at different frequencies
in a coarse-to-fine manner. To achieve this, we decompose the shadow image into
different frequency bands using Laplacian Pyramid. In addition, we introduce
two novel components to this model: the Attention-Aggregation Network and the
Gated Multi-scale Fusion Transformer. The Attention-Aggregation Network is
designed to remove shadows in the low-frequency part of the image, whereas the
Gated Multi-scale Fusion Transformer refines the entire image at a global scale
with its large perceptive field. Our extensive experiments demonstrate that
DocDeshadower outperforms the current state-of-the-art methods in both
qualitative and quantitative terms.
Related papers
- Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey [77.17812978009738]
The patterns of shadows are arbitrary, varied, and often have highly complex trace structures.
The degradation caused by shadows is spatially non-uniform, resulting in inconsistencies in illumination and color between shadow and non-shadow areas.
Recent developments in this field are primarily driven by deep learning-based solutions.
arXiv Detail & Related papers (2024-07-11T20:58:38Z) - ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer [41.008740643546226]
Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination.
We introduce a mask-free Shadow Removal and Refinement network (ShadowRefiner) via Fast Fourier Transformer.
Our method wins the championship in the Perceptual Track and achieves the second best performance in the Fidelity Track of NTIRE 2024 Image Shadow Removal Challenge.
arXiv Detail & Related papers (2024-04-18T03:53:33Z) - Progressive Recurrent Network for Shadow Removal [99.1928825224358]
Single-image shadow removal is a significant task that is still unresolved.
Most existing deep learning-based approaches attempt to remove the shadow directly, which can not deal with the shadow well.
We propose a simple but effective Progressive Recurrent Network (PRNet) to remove the shadow progressively.
arXiv Detail & Related papers (2023-11-01T11:42:45Z) - ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal [26.15238399758745]
We propose a Transformer-based architecture that integrates traditional methodologies and deep learning techniques to tackle the problem of document shadow removal.
The ShaDocFormer architecture comprises two components: the Shadow-attentive Threshold Detector (STD) and the Cascaded Fusion Refiner (CFR)
arXiv Detail & Related papers (2023-09-13T02:15:29Z) - SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow
Detection [85.16141353762445]
We treat the input shadow image as a composition of a background layer and a shadow layer, and design a Style-guided Dual-layer Disentanglement Network to model these layers independently.
Our model effectively minimizes the detrimental effects of background color, yielding superior performance on three public datasets with a real-time inference speed of 32 FPS.
arXiv Detail & Related papers (2023-08-17T12:10:51Z) - ShadowFormer: Global Context Helps Image Shadow Removal [41.742799378751364]
It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions.
We first propose a Retinex-based shadow model, from which we derive a novel transformer-based network, dubbed ShandowFormer.
A multi-scale channel attention framework is employed to hierarchically capture the global information.
We propose a Shadow-Interaction Module (SIM) with Shadow-Interaction Attention (SIA) in the bottleneck stage to effectively model the context correlation between shadow and non-shadow regions.
arXiv Detail & Related papers (2023-02-03T10:54:52Z) - ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document
Shadow Removal [53.01990632289937]
We propose a Transformer-based model for document shadow removal.
It uses shadow context encoding and decoding in both shadow and shadow-free regions.
arXiv Detail & Related papers (2022-11-30T01:46:29Z) - SpA-Former: Transformer image shadow detection and removal via spatial
attention [8.643096072885909]
We propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image.
Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one.
arXiv Detail & Related papers (2022-06-22T08:30:22Z) - Shadow-Aware Dynamic Convolution for Shadow Removal [80.82708225269684]
We introduce a novel Shadow-Aware Dynamic Convolution (SADC) module to decouple the interdependence between the shadow region and the non-shadow region.
Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module.
We develop a novel intra-convolution distillation loss to strengthen the information flow from the non-shadow region to the shadow region.
arXiv Detail & Related papers (2022-05-10T14:00:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.