VEMIC: View-aware Entropy model for Multi-view Image Compression


Susmija Jabbireddy (University of Maryland, College Park), Davit Soselia (University of Maryland, College Park), Max Ehrlich (University of Maryland, College Park), Christopher Metzler (University of Maryland, College Park), Amitabh Varshney (University of Maryland, College Park)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

With the ever-increasing amount of 3D data being captured and processed, multi-view image compression is essential to various applications, including virtual reality and 3D modeling. Despite the considerable success of learning-based compression models on single images, limited progress has been made in multi-view image compression. In this paper, we propose an efficient approach to multi-view image compression by leveraging the redundant information across different viewpoints without explicitly using warping operations or camera parameters. Our method builds upon the recent advancements in Multi-Reference Entropy Models (MEM), which were initially proposed to capture correlations within an image. We extend the MEM models to employ cross-view correlations in addition to within-image correlations. Specifically, we generate latent representations for each view independently and integrate a cross-view context module within the entropy model. The estimation of entropy parameters for each view follows an autoregressive technique, leveraging correlations with the previous views. We show that adding this view context module further enhances the compression performance when jointly trained with the autoencoder. Experimental results demonstrate superior performance compared to both traditional and learning-based multi-view compression methods.

Citation

@inproceedings{Jabbireddy_2024_BMVC,
author    = {Susmija Jabbireddy and Davit Soselia and Max Ehrlich and Christopher Metzler and Amitabh Varshney},
title     = {VEMIC: View-aware Entropy model for Multi-view Image Compression},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0606.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection