Developing effective 360-degree (spherical) image compression techniques is crucial for technologies like virtual reality and automated driving. This paper advances the state-of-the-art in on-the-sphere learning (OSLO) for omnidirectional image compression framework by proposing spherical attention modules, residual blocks, and a spatial autoregressive context model. These improvements achieve a 23.1% bit rate reduction in terms of WS-PSNR BD rate. Additionally, we introduce a spherical transposed convolution operator for upsampling, which reduces trainable parameters by a factor of four compared to the pixel shuffling used in the OSLO framework, while maintaining similar compression performance. Therefore, in total, our proposed method offers significant rate savings with a smaller architecture and can be applied to any spherical convolutional application.
@article{arxiv.2503.13119,
title = {OSLO-IC: On-the-Sphere Learned Omnidirectional Image Compression with Attention Modules and Spatial Context},
author = {Paul Wawerek-López and Navid Mahmoudian Bidgoli and Pascal Frossard and André Kaup and Thomas Maugey},
journal= {arXiv preprint arXiv:2503.13119},
year = {2025}
}
Comments
5 pages, 5 figures, accepted for IEEE International Conference on Acoustics, Speech and Signal Processing 2025 (IEEE ICASSP 2025)