FCNR: Fast Compressive Neural Representation of Visualization Images
This work addresses efficiency issues in neural compression for visualization images, offering incremental improvements over existing methods like NeRVI.
The paper tackles the problem of slow encoding and decoding speeds in neural compression for visualization images, achieving significant speed improvements while maintaining high reconstruction quality and compression ratio, with comparisons to state-of-the-art methods like E-NeRV, HNeRV, NeRVI, and ECSIC.
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.