Space-Angle Super-Resolution for Multi-View Images

Yuqi Sun, Ri Cheng, Bo Yan, Shili ZhouACM Multimedia 2021 · OpenReview

Abstract

The limited spatial and angular resolutions in multi-view multimedia applications restrict their visual experience in practical use. In this paper, we first argue the space-angle super-resolution (SASR) problem for irregular arranged multi-view images. It aims to increase the spatial resolution of source views and synthesize arbitrary virtual high resolution (HR) views between them jointly. One feasible solution is to perform super-resolution (SR) and view synthesis (VS) methods separately. However, it cannot fully exploit the intra-relationship between SR and VS tasks. Intuitively, multi-view images can provide more angular references, and higher resolution can provide more high-frequency details. Therefore, we propose a one-stage space-angle super-resolution network called SASRnet, which simultaneously synthesizes real and virtual HR views. Extensive experiments on several benchmarks demonstrate that our proposed method outperforms two-stage methods, meanwhile prove that SR and VS can promote each other. To our knowledge, this work is the first to address the SASR problem for unstructured multi-view images in an end-to-end learning-based manner.
BibTeX
@inproceedings{sun2021space,
  author = {Yuqi Sun and Ri Cheng and Bo Yan and Shili Zhou},
  title = {{Space-Angle Super-Resolution for Multi-View Images}},
  booktitle = {ACM Multimedia},
  year = {2021},
  url = {https://openreview.net/forum?id=tuPW-OFVC-k},
}

Loading related content...

Figure