标题:Image smoothing via unsupervised learning
作者:Fan, Qingnan ;Yang, Jiaolong ;Wipf, David ;Chen, Baoquan ;Tong, Xin
作者机构:[Fan, Qingnan ;Chen, Baoquan ] Shandong University, China;[Yang, Jiaolong ;Wipf, David ;Tong, Xin ] Microsoft Research Asia, United States;[Fan, Qingn 更多
会议名称:SIGGRAPH Asia 2018 Technical Papers - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH Asia 2018
会议日期:December 4, 2018 - December 7, 2018
来源:SIGGRAPH Asia 2018 Technical Papers, SIGGRAPH Asia 2018
出版年:2019
DOI:10.1145/3272127.3275081
摘要:Image smoothing represents a fundamental component of many disparate computer vision and graphics applications. In this paper, we present a unified unsupervised (label-free) learning framework that facilitates generating flexible and high-quality smoothing effects by directly learning from data using deep convolutional neural networks (CNNs). The heart of the design is the training signal as a novel energy function that includes an edge-preserving regularizer which helps maintain important yet potentially vulnerable image structures, and a spatially-adaptive Lp flattening criterion which imposes different forms of regularization onto different image regions for better smoothing quality. We implement a diverse set of image smoothing solutions employing the unified framework targeting various applications such as, image abstraction, pencil sketching, detail enhancement, texture removal and content-aware image manipulation, and obtain results comparable with or better than previous methods. Moreover, our method is extremely fast with a modern GPU (e.g, 200 fps for 1280×720 images).
© 2018 Association for Computing Machinery.
收录类别:EI
资源类型:会议论文
TOP