repository
HDR image reconstruction with deep learning
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | 선우명훈 | - |
| dc.contributor.author | 이병대 | - |
| dc.date.accessioned | 2022-11-29T03:01:18Z | - |
| dc.date.available | 2022-11-29T03:01:18Z | - |
| dc.date.issued | 2022-02 | - |
| dc.identifier.other | 31388 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/21002 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :전자공학과,2022. 2 | - |
| dc.description.tableofcontents | I. Introduction 1 II. Proposed Method 4 A. Brightening and Darkening Block 5 B. Blending Block 7 C. Loss Function 9 D. Data set 11 E. Hyper parameters 11 III. Experimental Results and Comparisons 12 A. Qualitative Comparison 12 B. Quantitative Comparison 14 C. Comparison With and Without Dynamic Loss 18 IV. Conclusion 20 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | HDR image reconstruction with deep learning | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.department | 일반대학원 전자공학과 | - |
| dc.date.awarded | 2022. 2 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 1245075 | - |
| dc.identifier.uci | I804:41038-000000031388 | - |
| dc.identifier.url | https://dcoll.ajou.ac.kr/dcollection/common/orgView/000000031388 | - |
| dc.subject.keyword | HDR 이미징 | - |
| dc.subject.keyword | 딥러닝 | - |
| dc.subject.keyword | 이미지 재구성 | - |
| dc.description.alternativeAbstract | To generate a high-quality HDR image, it is very important to restore the saturated irradiance information. To effectively restore saturated pixels, this paper proposes a method of generating an HDR image by combining the feature maps that made the input image brighter and darker, respectively. In addition, a loss function is proposed to focus on restoring the over-and under-exposed region with very high and low pixel values. Through the proposed loss function, the network can be focused on saturated pixel restoration during training. Compared to other methods, the proposed method showed an average of 9.1% higher results for HDR-visual difference predictor (VDP) and 46.7% higher results for SSIM than other methods. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Electronic Engineering > 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 :3,743,328
- Total Download :1,818
- Today View :20,986
