Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation
2026-07-01 • Machine Learning
Machine Learning
AI summaryⓘ
The authors present a new way to compress 3D volume data using explicit 3D Gaussian shapes to represent the data more efficiently. Unlike previous methods that needed extra mesh information to handle unstructured volumes, their method naturally encodes the shape of the data, saving space. They also created faster tools to train and sample their models, and developed strategies to improve accuracy. Their approach matches or beats existing methods in quality and speed, especially for unstructured volume data.
implicit neural representations3D Gaussian primitivesvolume data compressionunstructured volumesscalar field reconstructionCUDA accelerationsampling strategiesloss functionsmesh storagenovel view synthesis
Authors
Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar
Abstract
Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint. However, as existing INRs for unstructured volumes do not encode geometry, they require partial mesh storage for later sampling, limiting achievable compression. At the same time, novel view synthesis methods have shown that explicit collections of 3D Gaussians can be used to accurately visualize volume data. In this work, we introduce an explicit model for volume data compression based on 3D Gaussian primitives. We reinterpret collections of 3D Gaussians as an explicit representation of a scalar field and use a sampling strategy that reconstructs scalar values at spatial locations through weighted aggregation of intersecting Gaussians. We develop optimized CUDA-accelerated pipelines for structured and unstructured model sampling, loss functions that encourage accurate domain encoding by our models, and a novel sampling-error based densification strategy. Our explicit formulation naturally encodes domain geometry, eliminating the need for mesh storage in unstructured volumes and introducing significantly higher compression opportunities. Compared to existing INRs, we demonstrate that our explicit model achieves competitive reconstruction quality with significant training speedups on structured volumes, while markedly outperforming in all metrics on unstructured volumes.