FCNR: Fast Compressive Neural Representation of Visualization Images

TL;DR

FCNR introduces a rapid neural compression method for visualization images that significantly enhances encoding and decoding speeds while preserving high quality and compression ratios, outperforming existing neural methods.

Contribution

It presents FCNR, a novel neural compression technique that integrates stereo and context modules for faster processing of visualization images.

Findings

FCNR achieves faster encoding and decoding speeds.

Maintains high reconstruction quality.

Outperforms state-of-the-art neural compression methods.

Abstract

We present FCNR, a fast compressive neural representation for tens of thousands of visualization images under varying viewpoints and timesteps. The existing NeRVI solution, albeit enjoying a high compression ratio, incurs slow speeds in encoding and decoding. Built on the recent advances in stereo image compression, FCNR assimilates stereo context modules and joint context transfer modules to compress image pairs. Our solution significantly improves encoding and decoding speed while maintaining high reconstruction quality and satisfying compression ratio. To demonstrate its effectiveness, we compare FCNR with state-of-the-art neural compression methods, including E-NeRV, HNeRV, NeRVI, and ECSIC. The source code can be found at https://github.com/YunfeiLu0112/FCNR.