Super-resolved free-viewpoint image synthesis combined with sparse-representation-based super-resolution
Super-resolved free-viewpoint image synthesis combined with sparse-representation-based super-resolution
复制标题
DOI：
10.1109/apsipa.2013.6694248
复制
发表时间：
2013-10
期刊：
影响因子：
--
通讯作者：
Ryo Nakashima;Keita Takahashi;T. Naemura
中科院分区：
文献类型：
--
作者：
Ryo Nakashima;Keita Takahashi;T. Naemura
我们考虑超分辨自由视点图像合成（SR-FVS），其中将从虚拟视点观察到的高分辨率（HR）图像从一组低分辨率多视点图像合成。在以前的研究中，SR-FVS的方法提出了基于重建的超分辨率（RB-SR）的基础上。RB-SR使用多个图像来合成HR图像，从而可以自然地应用于SR-FVS，其中多视图图像作为输入。然而，合成图像的质量取决于观察条件，如目标场景的深度，所以有时SR-FVS的质量会严重下降。为了减轻这种退化，我们建议将基于学习的超分辨率（LB-SR）集成到SR-FVS过程中，LB-SR使用从大量自然图像中学习到的知识。本文采用稀疏编码超分辨率（ScSR）作为LB-SR方法，并将ScSR与已有的SR-FVS方法联合收割机相结合。
We consider super-resolved free-viewpoint image synthesis (SR-FVS), where a high-resolution (HR) image that would be observed from a virtual viewpoint is synthesized from a set of low-resolution multi-view images. In previous studies, methods for SR-FVS were proposed on the basis of reconstruction-based super-resolution (RB-SR). RB-SR uses multiple images to synthesize an HR image and thereby can naturally be applied to SR-FVS, where multi-view images are given as the input. However, the quality of the synthesized image depends on observation conditions such as the depth of the target scene, so sometimes the quality of SR-FVS can degrade severely. To mitigate such degradation, we propose integrating learning-based super-resolution (LB-SR), which uses knowledge learned from massive natural images, into the SR-FVS process. In this paper, we adopt sparse coding super-resolution (ScSR) as a LB-SR method and combine ScSR with an existing SR-FVS method.