Fully Convolutional Networks Based Reflection Separation for Light Field Images
碩士 === 國立中央大學 === 通訊工程學系 === 107 === Existing reflection separation schemes designed for multi-view images cannot be applied to light filed images due to the dense light fields with narrow baselines. In order to improve accuracy of the reconstructed background (i.e., the transmitted layer), most lig...
Main Authors: | Ruei-Yu Chang, 張瑞宇 |
---|---|
Other Authors: | Chih-Wei Tang |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/k6m8qh |
Similar Items
-
Microseismic Signal Denoising and Separation Based on Fully Convolutional Encoder–Decoder Network
by: Hang Zhang, et al.
Published: (2020-09-01) -
Region-Based Removal of Thermal Reflection Using Pruned Fully Convolutional Network
by: Ganbayar Batchuluun, et al.
Published: (2020-01-01) -
Skin Detection System based on Fully Convolutional Network and Hessian Matrix
by: LI,CHONG-RUEI, et al.
Published: (2018) -
Text Detection in Street View Images with Hierarchical Fully Convolution Neural Networks
by: Po-Wei Chang, et al.
Published: (2018) -
Polarized Light Field Imaging for Single-Shot Reflectance Separation
by: Jaewon Kim, et al.
Published: (2018-11-01)