Compression Artifact Reduction for 360-degree Images using Reference-based Deformable Convolutional Neural Network

  • Kim, Hee-Jae (Department of Electronic and Electrical Engineering, Ewha Womans University Graduate Program in Smart Factory) ;
  • Kang, Je-Won (Department of Electronic and Electrical Engineering, Ewha Womans University Graduate Program in Smart Factory) ;
  • Lee, Byung-Uk (Department of Electronic and Electrical Engineering, Ewha Womans University Graduate Program in Smart Factory)
  • Published : 2021.11.26

Abstract

In this paper, we propose an efficient reference-based compression artifact reduction network for 360-degree images in an equi-rectangular projection (ERP) domain. In our insight, conventional image restoration methods cannot be applied straightforwardly to 360-degree images due to the spherical distortion. To address this problem, we propose an adaptive disparity estimator using a deformable convolution to exploit correlation among 360-degree images. With the help of the proposed convolution, the disparity estimator establishes the spatial correspondence successfully between the ERPs and extract matched textures to be used for image restoration. The experimental results demonstrate that the proposed algorithm provides reliable high-quality textures from the reference and improves the quality of the restored image as compared to the state-of-the-art single image restoration methods.

Keywords

Acknowledgement

This work has been supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)(No.NRF-2019R1C1C1010249). This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2020-0-00920, Development of Ultra High Resolution Unstructured Plenoptic Video Storage/Compression/Streaming Technology for Medium to Large Space)