HDR image reconstruction with deep learning
- 주제(키워드) 딥러닝 , HDR 이미징 , 이미지 재구성
- 주제(DDC) 621.381
- 발행기관 아주대학교
- 지도교수 선우명훈
- 발행년도 2022
- 학위수여년월 2022. 2
- 학위명 석사
- 학과 및 전공 일반대학원 전자공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000031388
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
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.
more목차
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