A CNN-based Post-Processor for Perceptually-Optimized Immersive Media Compression

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

156 Downloads (Pure)

Abstract

In recent years, resolution adaptation based on deep neural networks has enabled significant performance gains for conventional (2D) video codecs. This paper investigates the effectiveness of spatial resolution resampling in the context of immersive content. The proposed approach reduces the spatial resolution of input multi-view videos before encoding, and reconstructs their original resolution after decoding. During the up-sampling process, an advanced CNN model is used to reduce potential re-sampling, compression, and synthesis artifacts. This work has been fully tested with the TMIV coding standard using a Versatile Video Coding (VVC) codec. The results demonstrate that the proposed method achieves a significant rate-quality performance improvement for the majority of the test sequences, with an average BD-VMAF improvement of 3.07 overall sequences.
Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing (ICIP)
PublisherIEEE Computer Society
ISBN (Electronic)978-1-6654-9620-9
ISBN (Print)978-1-6654-9621-6
DOIs
Publication statusPublished - 18 Oct 2022

Keywords

  • eess.IV

Fingerprint

Dive into the research topics of 'A CNN-based Post-Processor for Perceptually-Optimized Immersive Media Compression'. Together they form a unique fingerprint.

Cite this