Fast Neural Representations for Direct Volume Rendering

TL;DR

This paper introduces a GPU-optimized neural scene representation network for efficient, high-quality volume rendering, enabling faster decoding, lower memory use, and flexible temporal reconstruction for practical applications.

Contribution

It presents a novel GPU tensor core-based neural network architecture that improves compression, speed, and temporal reconstruction capabilities over existing methods.

Findings

Competitive quality at high compression rates

Significantly faster decoding times

Lower memory consumption during reconstruction

Abstract

Despite the potential of neural scene representations to effectively compress 3D scalar fields at high reconstruction quality, the computational complexity of the training and data reconstruction step using scene representation networks limits their use in practical applications. In this paper, we analyze whether scene representation networks can be modified to reduce these limitations and whether such architectures can also be used for temporal reconstruction tasks. We propose a novel design of scene representation networks using GPU tensor cores to integrate the reconstruction seamlessly into on-chip raytracing kernels, and compare the quality and performance of this network to alternative network- and non-network-based compression schemes. The results indicate competitive quality of our design at high compression rates, and significantly faster decoding times and lower memory consumption during data reconstruction. We investigate how density gradients can be computed using the network and show an extension where density, gradient and curvature are predicted jointly. As an alternative to spatial super-resolution approaches for time-varying fields, we propose a solution that builds upon latent-space interpolation to enable random access reconstruction at arbitrary granularity. We summarize our findings in the form of an assessment of the strengths and limitations of scene representation networks \changed{for compression domain volume rendering, and outline future research directions.