Light-field view synthesis using convolutional block attention module

M. Shahzeb Khan Gul, M. Umair Mukati, Michel Bätz, Søren Forchhammer, Joachim Keinert

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

65 Downloads (Pure)

Abstract

Consumer light-field (LF) cameras suffer from a low or limited resolution because of the angular-spatial trade-off. To alleviate this drawback, we propose a novel learning-based approach utilizing attention mechanism to synthesize novel views of a light-field image using a sparse set of input views (i.e., 4 corner views) from a camera array. In the proposed method, we divide the process into three stages, stereo-feature extraction, disparity estimation, and final image refinement. We use three sequential convolutional neural networks for each stage. A residual convolutional block attention module (CBAM) is employed for final adaptive image refinement. Attention modules are helpful in learning and focusing more on the important features of the image and are thus sequentially applied in the channel and spatial dimensions. Experimental results show the robustness of the proposed method. Our proposed network outperforms the state-of-the-art learning-based light-field view synthesis methods on two challenging real-world datasets by 0.5 dB on average. Furthermore, we provide an ablation study to substantiate our findings.

Original languageEnglish
Title of host publicationProceedings of 2021 IEEE International Conference on Image Processing
PublisherIEEE
Publication date2021
Pages3398-3402
ISBN (Electronic)9781665441155
DOIs
Publication statusPublished - 2021
Event28th IEEE International Conference on Image Processing - Anchorage, United States
Duration: 19 Sept 202122 Sept 2021
https://www.2021.ieeeicip.org/www.2021.ieeeicip.org/index.html

Conference

Conference28th IEEE International Conference on Image Processing
Country/TerritoryUnited States
CityAnchorage
Period19/09/202122/09/2021
SponsorIEEE
Internet address

Keywords

  • Deep-learning
  • Light-field
  • View synthesis

Fingerprint

Dive into the research topics of 'Light-field view synthesis using convolutional block attention module'. Together they form a unique fingerprint.

Cite this