IEEE VIS 2024 Content: FCNR: Fast Compressive Neural Representation of Visualization Images

FCNR: Fast Compressive Neural Representation of Visualization Images



Yunfei Lu - University of Notre Dame, Notre Dame, United States

 Pengfei Gu - University of Notre Dame, Notre Dame, United States

 Chaoli Wang - University of Notre Dame, Notre Dame, United States

 Screen-reader Accessible PDF

 Download Supplemental Material

 Room: Bayshore VI

2024-10-16T18:21:00ZGMT-0600Change your timezone on the schedule page
2024-10-16T18:21:00Z

Exemplar figure, described by caption below — FCNR is a fast method for compressing a great number of visualization images. It stands out in both encoding and decoding speed, and leads to compressive results while maintains high reconstruction quality using neural representations.

Fast forward

Full Video

Keywords

Machine Learning Techniques, Image and Video Data

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.