Leveraging Scene Geometry and Depth Information for Robust Image Deraining
Image deraining holds great potential for enhancing the vision of autonomous vehicles in rainy conditions, contributing to safer driving. Previous works have primarily focused on employing a single network architecture to generate derained images. However, they often fail to fully exploit the rich p...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/14/1/11 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588757203681280 |
|---|---|
| author | Ningning Xu Jidong J. Yang |
| author_facet | Ningning Xu Jidong J. Yang |
| author_sort | Ningning Xu |
| collection | DOAJ |
| description | Image deraining holds great potential for enhancing the vision of autonomous vehicles in rainy conditions, contributing to safer driving. Previous works have primarily focused on employing a single network architecture to generate derained images. However, they often fail to fully exploit the rich prior knowledge embedded in the scenes. Particularly, most methods overlook the depth information that can provide valuable context about scene geometry and guide more robust deraining. In this work, we introduce a novel learning framework that integrates multiple networks: an AutoEncoder for deraining, an auxiliary network to incorporate depth information, and two supervision networks to enforce feature consistency between rainy and clear scenes. This multi-network design enables our model to effectively capture the underlying scene structure, producing clearer and more accurately derained images, leading to improved object detection for autonomous vehicles. Extensive experiments on three widely used datasets demonstrated the effectiveness of our proposed method. |
| format | Article |
| id | doaj-art-3cd276c50a5345e898ff4846632d368d |
| institution | Kabale University |
| issn | 2073-431X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-3cd276c50a5345e898ff4846632d368d2025-01-24T13:27:52ZengMDPI AGComputers2073-431X2025-01-011411110.3390/computers14010011Leveraging Scene Geometry and Depth Information for Robust Image DerainingNingning Xu0Jidong J. Yang1Smart Mobility and Infrastructure Lab, College of Engineering, University of Georgia, Athens, GA 30602, USASmart Mobility and Infrastructure Lab, College of Engineering, University of Georgia, Athens, GA 30602, USAImage deraining holds great potential for enhancing the vision of autonomous vehicles in rainy conditions, contributing to safer driving. Previous works have primarily focused on employing a single network architecture to generate derained images. However, they often fail to fully exploit the rich prior knowledge embedded in the scenes. Particularly, most methods overlook the depth information that can provide valuable context about scene geometry and guide more robust deraining. In this work, we introduce a novel learning framework that integrates multiple networks: an AutoEncoder for deraining, an auxiliary network to incorporate depth information, and two supervision networks to enforce feature consistency between rainy and clear scenes. This multi-network design enables our model to effectively capture the underlying scene structure, producing clearer and more accurately derained images, leading to improved object detection for autonomous vehicles. Extensive experiments on three widely used datasets demonstrated the effectiveness of our proposed method.https://www.mdpi.com/2073-431X/14/1/11image derainingAutoEncoderprior knowledgesupervision networksfeature consistencydepth information |
| spellingShingle | Ningning Xu Jidong J. Yang Leveraging Scene Geometry and Depth Information for Robust Image Deraining Computers image deraining AutoEncoder prior knowledge supervision networks feature consistency depth information |
| title | Leveraging Scene Geometry and Depth Information for Robust Image Deraining |
| title_full | Leveraging Scene Geometry and Depth Information for Robust Image Deraining |
| title_fullStr | Leveraging Scene Geometry and Depth Information for Robust Image Deraining |
| title_full_unstemmed | Leveraging Scene Geometry and Depth Information for Robust Image Deraining |
| title_short | Leveraging Scene Geometry and Depth Information for Robust Image Deraining |
| title_sort | leveraging scene geometry and depth information for robust image deraining |
| topic | image deraining AutoEncoder prior knowledge supervision networks feature consistency depth information |
| url | https://www.mdpi.com/2073-431X/14/1/11 |
| work_keys_str_mv | AT ningningxu leveragingscenegeometryanddepthinformationforrobustimagederaining AT jidongjyang leveragingscenegeometryanddepthinformationforrobustimagederaining |