repository
Multi-Degraded Image Restoration Using Spatial Distortion information
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | 손경아 | - |
| dc.contributor.author | 신욱수 | - |
| dc.date.accessioned | 2022-11-29T03:01:08Z | - |
| dc.date.available | 2022-11-29T03:01:08Z | - |
| dc.date.issued | 2022-02 | - |
| dc.identifier.other | 31416 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/20793 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :인공지능학과,2022. 2 | - |
| dc.description.tableofcontents | 1. Introduction 1 2. Related Works 5 2.1. Image Restoration 5 2.2. Multi-Degraded Image Dataset 5 2.3. Information Injection 6 3. Integrated Multi Distortion Dataset 8 4. Methods 11 4.1. Recognition Network 11 4.2. Reconstruction Network 13 5. Experiments 16 5.1. Implementation Details 16 5.2. Comparison with Other Methods 17 5.2.1. Comparative Methods 17 5.2.2. Comparison Results 18 5.3. Analysis of Recognition Network 20 5.4. IMDD with other distortions 21 6. Conclusion 23 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Multi-Degraded Image Restoration Using Spatial Distortion information | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.department | 일반대학원 인공지능학과 | - |
| dc.date.awarded | 2022. 2 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 1245087 | - |
| dc.identifier.uci | I804:41038-000000031416 | - |
| dc.identifier.url | https://dcoll.ajou.ac.kr/dcollection/common/orgView/000000031416 | - |
| dc.subject.keyword | image resotration | - |
| dc.description.alternativeAbstract | A lot of research has been conducted on image restoration, which is a problem of restoring a distorted image to a clean image. Recently, Many tasks in the image restoration field are showing tremendous performance improvement due to the advancement of deep learning. In particular, for real-world applications such as autopilot vision or multi-camera sys- tems, some datasets using multiple distortions have been studied in recent years. Based on the method of applying multiple distortions to the images, these datasets are broadly classified into two types: sequentially applied to the entire image, and applied differently for each divided section of the image. The model trained through the dataset created in the first method is weak in restoring a single distortion images, and the model trained in the dataset created in the second method is weak in restoring the mixed distortion images. Therefore, we propose the Integrated Multiple Distortion Dataset by fusing these two types of methods. The proposed IMDD is a useful dataset that can be trained in sit- uations where multi-distortions are assumed by supplementing the shortcomings of the two datasets. Additionally, we propose a Spatial Distortion Information Transfer Net- work(SDITNet) consisting of a reconstruction network that restores a multi-distorted image and a recognition network that predicts the spatial distortion information of the multi-distorted image to deliver it to the reconstruction network. We find that we show that our model outperforms other models for both single-distortion and multi-distortion reconstructions, and that the transfer of spatial distortion information obtained through the recognition network helps to improve the reconstruction performance. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Artificial Intelligence > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,725,667
- Total Download :1,818
- Today View :3,325
