Compressive Neural Representations of Volumetric Scalar Fields

We present an approach for compressing volumetric scalar fields using implicit neural representations. Our approach represents a scalar field as a learned function, wherein a neural network maps a point in the domain to an output scalar value. By setting the number of weights of the neural network to be smaller than the input size, we achieve compressed representations of scalar fields, thus framing compression as a type of function approximation. Combined with carefully quantizing network weights, we show that this approach yields highly compact representations that outperform state-of-the-art volume compression approaches. The conceptual simplicity of our approach enables a number of benefits, such as support for time-varying scalar fields, optimizing to preserve spatial gradients, and random-access field evaluation. We study the impact of network design choices on compression performance, highlighting how simple network architectures are effective for a broad range of volumes.

Automated summary

The proposed approach presents a method for compressing volumetric scalar fields using implicit neural representations, achieving highly compact representations by quantizing network weights and outperforming state-of-the-art compression methods. The conceptual simplicity of the approach allows for multiple benefits such as support for time-varying scalar fields and random-access field evaluation.