# GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction Source: [GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction]() Collection index: [llms.txt]() Data updated: 2026-03-25T05:00:04.214Z Authors: Di Kong, Yikai Wang, Wenjie Guo, Yifan Bu, Boya Zhang, Yuexin Duan, Xiawei Yue, Wenbiao Du, Yiman Zhong, Yuwen Chen, Cheng Ma Published: 2026-03-21T03:10:27.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [2D Slice Reconstruction on ABUS](): 2D Slice Reconstruction; ABUS; PSNR: 33.07. - [2D Slice Reconstruction on rDL-LSM](): 2D Slice Reconstruction; rDL-LSM; PSNR: 34.57. - [2D Slice Reconstruction on TNNI1](): 2D Slice Reconstruction; TNNI1; PSNR: 42.08. - [2D Slice Reconstruction on hiPSC](): 2D Slice Reconstruction; hiPSC; PSNR: 32.59. - [2D Slice Reconstruction on Tribolium](): 2D Slice Reconstruction; Tribolium; PSNR: 36.14. - [3D Volumetric Reconstruction on ABUS](): 3D Volumetric Reconstruction; ABUS; PSNR: 33.22. - [3D Volumetric Reconstruction on rDL-LSM](): 3D Volumetric Reconstruction; rDL-LSM; PSNR: 34.47. - [3D Volumetric Reconstruction on TNNI1](): 3D Volumetric Reconstruction; TNNI1; PSNR: 40.17. - [3D Volumetric Reconstruction on hiPSC](): 3D Volumetric Reconstruction; hiPSC; PSNR: 33.73. - [3D Volumetric Reconstruction on Tribolium](): 3D Volumetric Reconstruction; Tribolium; PSNR: 35.05. - [3D Volume Reconstruction on ISBI12](): 3D Volume Reconstruction; ISBI12; 2D PSNR: 28.79. - [3D Volume Reconstruction on CREMI](): 3D Volume Reconstruction; CREMI; 2D PSNR: 29.5. ## Original sources and implementation [Original paper]() [PDF]()