CECNN: A Convergent Error Concealment Neural Network for Videos

Razib Iqbal, Shashi Khanal, Mohammad Kazemi

2022

Abstract

In video error concealment, we estimate any missing information in the video frames as close to the actual data. In this paper, we present a video error concealment technique, named Convergent Error Concealment Neural Network (CECNN), based on Convolutional Neural Network (CNN). CECNN is a two-stage process where it first learns to predict voxel information from the training dataset. It then applies transfer learning using the pre-trained model from the first stage to produce intermediate outputs. CECNN consists of dedicated paths for the past and future frames to produce the intermediate outputs, which are then combined to fill the missing information in the errored frame. The quality of the outputs from CECNN is compared with other techniques, such as motion vector estimation, error concealment using neighboring motion vectors, and generative image inpainting. The evaluation results suggest that our CECNN approach would be a good candidate for error concealment in video decoders.

Paper Citation

in Harvard Style

Iqbal R., Khanal S. and Kazemi M. (2022). CECNN: A Convergent Error Concealment Neural Network for Videos. In Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, ISBN 978-989-758-591-3, pages 23-31. DOI: 10.5220/0011275800003289

in Bibtex Style

@conference{sigmap22,
author={Razib Iqbal and Shashi Khanal and Mohammad Kazemi},
title={CECNN: A Convergent Error Concealment Neural Network for Videos},
booktitle={Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP,},
year={2022},
pages={23-31},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011275800003289},
isbn={978-989-758-591-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP,
TI - CECNN: A Convergent Error Concealment Neural Network for Videos
SN - 978-989-758-591-3
AU - Iqbal R.
AU - Khanal S.
AU - Kazemi M.
PY - 2022
SP - 23
EP - 31
DO - 10.5220/0011275800003289