Using Convolutional Neural Network to Reconstruct High Dynamic Range Image from a Single Low Dynamic Range Image
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 106 === We present a learning-based approach for recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image. This problem is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of ca...
Main Authors: | Yi-Lung Kao, 高以龍 |
---|---|
Other Authors: | Ming Ouhyoung |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/e6d59u |
Similar Items
-
Single-Shot High Dynamic Range Imaging via Multiscale Convolutional Neural Network
by: An Gia Vien, et al.
Published: (2021-01-01) -
Deep Residual Neural Network Design for Converting the Low Dynamic Range Image to the High Dynamic Range Image
by: ZHANG, JIA-WEI, et al.
Published: (2019) -
Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image
by: Siyeong Lee, et al.
Published: (2018-01-01) -
A hardware design for converting the low dynamic range image to the high dynamic range image
by: WU,CHIA-CHIN, et al.
Published: (2018) -
High Dynamic Range Image Generation and Coding for Multi-view Images
by: Kao, Pohan, et al.
Published: (2012)