Use Partial Convolution to solve SRCNN’s pixel loss of picture
碩士 === 國立臺北大學 === 統計學系 === 108 === Super-Resolution imaging (SR) is a technique for improving image resolution. Images can be divided into movies and pictures. In this paper, we want to perform super-resolution imaging on single images . At present, the methods for improving the resolution are gener...
Main Authors: | HSU, WEI-HAN, 許巍瀚 |
---|---|
Other Authors: | WANG, CHUN-CHAO |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/47v8gr |
Similar Items
-
Research on Population Spatialization Method Based on PMST-SRCNN
by: Li Yuting, et al.
Published: (2020-01-01) -
Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number
by: Windra Swastika, et al.
Published: (2020-10-01) -
Underwater Image High Definition Display Using the Multilayer Perceptron and Color Feature-Based SRCNN
by: Yujie Li, et al.
Published: (2019-01-01) -
Handling Invalid Pixels in Convolutional Neural Networks
by: Messou, Ehounoud Joseph Christopher
Published: (2020) -
Missing Pixel Reconstruction on Landsat 8 Analysis Ready Data Land Surface Temperature Image Patches Using Source-Augmented Partial Convolution
by: Maosi Chen, et al.
Published: (2020-09-01)