GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction

2026-03-20

AI Summary

This work addresses the challenge of preserving fine internal structures in volumetric data under high compression ratios, which is critical for subsequent analysis. The authors propose a novel approach that integrates 3D Gaussian splatting with an imaging-system-aware focus model. Key innovations include a slice-aware anisotropic Gaussian stacking strategy, a differentiable projection operator encoding a point spread function of finite thickness, and a compact Gaussian representation framework that jointly optimizes reconstruction quality and compression efficiency. Evaluated on microscopy and ultrasound datasets, the method achieves up to 16× voxel compression while delivering diagnostic-grade fidelity. It accelerates reconstruction by up to 11× compared to NeRF—reaching as fast as three minutes—and enables rapid 2D/3D visualization without compromising structural detail.

Technology Category

• Computer Vision: 3D Computer Vision
• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Slice-based volumetric imaging is widely applied and it demands representations that compress aggressively while preserving internal structure for analysis. We introduce GaussianPile, unifying 3D Gaussian splatting with an imaging system-aware focus model to address this challenge. Our proposed method introduces three key innovations: (i) a slice-aware piling strategy that positions anisotropic 3D Gaussians to model through-slice contributions, (ii) a differentiable projection operator that encodes the finite-thickness point spread function of the imaging acquisition system, and (iii) a compact encoding and joint optimization pipeline that simultaneously reconstructs and compresses the Gaussian sets. Our CUDA-based design retains the compression and real-time rendering efficiency of Gaussian primitives while preserving high-frequency internal volumetric detail. Experiments on microscopy and ultrasound datasets demonstrate that our method reduces storage and reconstruction cost, sustains diagnostic fidelity, and enables fast 2D visualization, along with 3D voxelization. In practice, it delivers high-quality results in as few as 3 minutes, up to 11x faster than NeRF-based approaches, and achieves consistent 16x compression over voxel grids, offering a practical path to deployable compression and exploration of slice-based volumetric datasets.

Problem

• slice-based volumetric imaging
• data compression
• internal structure preservation
• volumetric reconstruction

Innovation

• Gaussian Splatting
• Slice-based Volumetric Reconstruction
• Differentiable Projection
• Joint Optimization
• Compression