Accelerated Volumetric Compression without Hierarchies: A Fourier Feature Based Implicit Neural Representation Approach

TL;DR

This paper presents a fast, structure-free neural volumetric compression method using Fourier features and selective voxel sampling, achieving high compression rates and reduced training time without hierarchical metadata.

Contribution

It introduces a novel, hierarchy-free neural compression approach combining Fourier features with dynamic voxel sampling for efficient volumetric data representation.

Findings

Reduced training time by 63.7% with minor quality loss

Achieved a compression rate of 14 with neural network weights

Eliminated traditional data-loading overhead in volumetric compression

Abstract

Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective voxel sampling, yielding compact volumetric representations and faster convergence. Our dynamic voxel selection uses morphological dilation to prioritize active regions, reducing redundant computation without any hierarchical metadata. In the experiment, sparse training reduced training time by 63.7 % (from 30 to 11 minutes) with only minor quality loss: PSNR dropped 0.59 dB (from 32.60 to 32.01) and SSIM by 0.008 (from 0.948 to 0.940). The resulting neural representation, stored solely as network weights, achieves a compression rate of 14 and eliminates traditional data-loading overhead. This connects coordinate-based neural representation with efficient volumetric compression, offering a scalable, structure-free solution for practical applications.