Image Completion via MultiScale Generative Adversarial Networks and Edge Cues
碩士 === 國立臺灣科技大學 === 資訊工程系 === 107 === Recent deep learningbased approaches have shown significant improvements in image completion. However, the existing methods often create distorted structures or blurry textures inconsistent with surrounding areas. This is mainly due to the ineffectiveness of co...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/ps7bck |