Evaluating the true potential of diffusion-based inpainting in a compression context
详细信息 查看全文
- 作者：Pascal Petera ; peter@mia.uni-saarland.de" class="auth_mail" title="E-mail the corresponding author ; Sebastian Hoffmanna ; hoffmann@mia.uni-saarland.de" class="auth_mail" title="E-mail the corresponding author ; Frank Nedweda ; nedwed@mia.uni-saarland.de" class="auth_mail" title="E-mail the corresponding author ; Laurent Hoeltgenb ; hoeltgen@b-tu.de" class="auth_mail" title="E-mail the corresponding author ; Joachim Weickerta ; weickert@mia.uni-saarland.de" class="auth_mail" title="E-mail the corresponding author
- 关键词：Diffusion inpainting ; Image compression ; Probabilistic tree-densification
- 刊名：Signal Processing: Image Communication
- 出版年：2016
- 出版时间：August 2016
- 年：2016
- 卷：46
- 期：Complete
- 页码：40-53
- 全文大小：3122 K
文摘
- •
PDEs for compression can only be properly evaluated in the context of actual codecs.
- •
Simple linear PDEs can be competitive with optimised known data.
- •
Sophisticated anisotropic PDEs are well-suited for suboptimal known data.