Cross-Modal Spherical Aggregation for Weakly Supervised Remote Sensing Shadow Removal
- URL: http://arxiv.org/abs/2406.17469v1
- Date: Tue, 25 Jun 2024 11:14:09 GMT
- Title: Cross-Modal Spherical Aggregation for Weakly Supervised Remote Sensing Shadow Removal
- Authors: Kaichen Chi, Wei Jing, Junjie Li, Qiang Li, Qi Wang,
- Abstract summary: We propose a weakly supervised shadow removal network with a spherical feature space, dubbed S2-ShadowNet, to explore the best of both worlds for visible and infrared modalities.
Specifically, we employ a modal translation (visible-to-infrared) model to learn the cross-domain mapping, thus generating realistic infrared samples.
We contribute a large-scale weakly supervised shadow removal benchmark, including 4000 shadow images with corresponding shadow masks.
- Score: 22.4845448174729
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Remote sensing shadow removal, which aims to recover contaminated surface information, is tricky since shadows typically display overwhelmingly low illumination intensities. In contrast, the infrared image is robust toward significant light changes, providing visual clues complementary to the visible image. Nevertheless, the existing methods ignore the collaboration between heterogeneous modalities, leading to undesired quality degradation. To fill this gap, we propose a weakly supervised shadow removal network with a spherical feature space, dubbed S2-ShadowNet, to explore the best of both worlds for visible and infrared modalities. Specifically, we employ a modal translation (visible-to-infrared) model to learn the cross-domain mapping, thus generating realistic infrared samples. Then, Swin Transformer is utilized to extract strong representational visible/infrared features. Simultaneously, the extracted features are mapped to the smooth spherical manifold, which alleviates the domain shift through regularization. Well-designed similarity loss and orthogonality loss are embedded into the spherical space, prompting the separation of private visible/infrared features and the alignment of shared visible/infrared features through constraints on both representation content and orientation. Such a manner encourages implicit reciprocity between modalities, thus providing a novel insight into shadow removal. Notably, ground truth is not available in practice, thus S2-ShadowNet is trained by cropping shadow and shadow-free patches from the shadow image itself, avoiding stereotypical and strict pair data acquisition. More importantly, we contribute a large-scale weakly supervised shadow removal benchmark, including 4000 shadow images with corresponding shadow masks.
Related papers
- SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection [90.4751446041017]
We present SwinShadow, a transformer-based architecture that fully utilizes the powerful shifted window mechanism for detecting adjacent shadows.
The whole process can be divided into three parts: encoder, decoder, and feature integration.
Experiments on three shadow detection benchmark datasets, SBU, UCF, and ISTD, demonstrate that our network achieves good performance in terms of balance error rate (BER)
arXiv Detail & Related papers (2024-08-07T03:16:33Z) - Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey [78.84004293081631]
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) - SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and
Illumination Removal in High-Illuminance Scenes [51.50157919750782]
We present SIRe-IR, an implicit neural rendering inverse approach that decomposes the scene into environment map, albedo, and roughness.
By accurately modeling the indirect radiance field, normal, visibility, and direct light simultaneously, we are able to remove both shadows and indirect illumination.
Even in the presence of intense illumination, our method recovers high-quality albedo and roughness with no shadow interference.
arXiv Detail & Related papers (2023-10-19T10:44:23Z) - Learning Restoration is Not Enough: Transfering Identical Mapping for
Single-Image Shadow Removal [19.391619888009064]
State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs.
We find that two tasks exhibit poor compatibility, and using shared weights for these two tasks could lead to the model being optimized towards only one task.
We propose to handle these two tasks separately and leverage the identical mapping results to guide the shadow restoration in an iterative manner.
arXiv Detail & Related papers (2023-05-18T01:36:23Z) - Leveraging Inpainting for Single-Image Shadow Removal [29.679542372017373]
In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly.
A naive encoder-decoder network gets competitive restoration quality w.r.t. the state-of-the-art methods via only 10% shadow & shadow-free image pairs.
Inspired by these observations, we formulate shadow removal as an adaptive fusion task that takes advantage of both shadow removal and image inpainting.
arXiv Detail & Related papers (2023-02-10T16:21:07Z) - 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) - Structure-Informed Shadow Removal Networks [67.57092870994029]
Existing deep learning-based shadow removal methods still produce images with shadow remnants.
We propose a novel structure-informed shadow removal network (StructNet) to leverage the image-structure information to address the shadow remnant problem.
Our method outperforms existing shadow removal methods, and our StructNet can be integrated with existing methods to improve them further.
arXiv Detail & Related papers (2023-01-09T06:31:52Z) - CRFormer: A Cross-Region Transformer for Shadow Removal [27.67680052355886]
We propose a novel cross-region transformer, namely CRFormer, for shadow removal.
This is achieved by a carefully designed region-aware cross-attention operation.
Experiments on ISTD, AISTD, SRD, and Video Shadow Removal datasets demonstrate the superiority of our method.
arXiv Detail & Related papers (2022-07-04T17:33:02Z) - 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) - R2D: Learning Shadow Removal to Enhance Fine-Context Shadow Detection [64.10636296274168]
Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges.
We propose a new method called Restore to Detect (R2D), where a deep neural network is trained for restoration (shadow removal)
We show that our proposed method R2D improves the shadow detection performance while being able to detect fine context better compared to the other recent methods.
arXiv Detail & Related papers (2021-09-20T15:09:22Z)
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.