NeRVI: Compressive neural representation of visualization images for communicating volume visualization results.

We present NeRVI, a new deep-learning approach that compresses a large collection of visualization images generated from time-varying data for communicating volume visualization results. Based on an image-based implicit neural representation, our approach represents tens of thousands of high-resolution rendering images parameterized by different parameters via a hybrid model of multilayer perceptrons and convolutional neural networks. Our model predicts images and corresponding masks, and the masks are utilized for loss computation and network training to capture fine structural details and small components. In conjunction with model quantization and weight encoding, NeRVI yields highly compact compressive neural representations while preserving the image fidelity well. We demonstrate the effectiveness of NeRVI with isosurface rendering and direct volume rendering images generated from multiple data sets and compare NeRVI with other state-of-the-art deep learning-based (InSituNet, SIREN, NeRF, and NeRV) methods. Quantitative and qualitative results show that NeRVI provides an alternative solution that augments domain scientists' ability to manage, represent, and communicate scientific visualization output. [Display omitted] • Implementing an image-wise implicit neural representation for compressive representation of visualization images. • Proposing SIREN-based residual blocks for performance improvement. • Presenting mask loss for addressing the foreground–background issue well and capturing small objects well. • Achieving high-quality visualization images compression with a high compression rate (705 to 1,263). [ABSTRACT FROM AUTHOR]