中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共6条，第1-6条 帮助

已选(0)清除 条数/页：   排序方式：
W-Net: Structure and Texture Interaction for Image Inpainting 期刊论文
IEEE Transactions on Multimedia, 2022, 卷号: 25, 页码: 1-12
作者:  Zhang, Ruisong;  Quan, Weize;  Zhang, Yong;  Wang, Jue;  Yan, Dong-Ming
收藏  |  浏览/下载：75/0  |  提交时间：2023/04/25
Index Terms-Image inpainting  structure and texture  convolutional neural network  attention  
Image Inpainting With Local and Global Refinement 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2405-2420
作者:  Quan, Weize;  Zhang, Ruisong;  Zhang, Yong;  Li, Zhifeng;  Wang, Jue;  Yan, Dong-Ming
收藏  |  浏览/下载：253/0  |  提交时间：2022/06/06
Image reconstruction  Generators  Convolution  Semantics  Image edge detection  Deep learning  Task analysis  Image inpainting  neural networks  receptive field  
Pixel-wise Dense Detector for Image Inpainting 期刊论文
COMPUTER GRAPHICS FORUM, 2020, 卷号: 39, 期号: 7, 页码: 471-482
作者:  Zhang, Ruisong;  Quan, Weize;  Wu, Baoyuan;  Li, Zhifeng;  Yan, Dong-Ming
收藏  |  浏览/下载：208/0  |  提交时间：2021/03/29
Distinguishing Computer-Generated Images from Natural Images Using Channel and Pixel Correlation 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2020, 卷号: 35, 期号: 3, 页码: 592-602
作者:  Zhang, Rui-Song;  Quan, Wei-Ze;  Fan, Lu-Bin;  Hu, Li-Ming;  Yan, Dong-Ming
收藏  |  浏览/下载：204/0  |  提交时间：2020/07/20
natural image  computer-generated image  channel and pixel correlation  convolutional neural network  
Distinguishing Computer-Generated Images from Natural Images Using Channel and Pixel Correlation 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2020, 卷号: 35, 期号: 3, 页码: 592-602
作者:  Zhang, Rui-Song;  Quan, Wei-Ze;  Fan, Lu-Bin;  Hu, Li-Ming;  Yan, Dong-Ming
收藏  |  浏览/下载：199/0  |  提交时间：2020/07/20
natural image  computer-generated image  channel and pixel correlation  convolutional neural network  
CONICS-BASED STEREO, MOTION ESTIMATION, AND POSE DETERMINATION 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1993, 卷号: 10, 期号: 1, 页码: 7-25
作者:  SONG, DM
收藏  |  浏览/下载：51/0  |  提交时间：2018/10/10