Advancing Structured Priors for Sparse-Voxel Surface Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chi, Ting-Hsun, Chen, Chu-Rong, Hsu, Chi-Tun, Lin, Hsuan-Ting, Huang, Sheng-Yu, Sun, Cheng, Wang, Yu-Chiang Frank
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911396999987200
author Chi, Ting-Hsun
Chen, Chu-Rong
Hsu, Chi-Tun
Lin, Hsuan-Ting
Huang, Sheng-Yu
Sun, Cheng
Wang, Yu-Chiang Frank
author_facet Chi, Ting-Hsun
Chen, Chu-Rong
Hsu, Chi-Tun
Lin, Hsuan-Ting
Huang, Sheng-Yu
Sun, Cheng
Wang, Yu-Chiang Frank
contents Reconstructing accurate surfaces with radiance fields has progressed rapidly, yet two promising explicit representations, 3D Gaussian Splatting and sparse-voxel rasterization, exhibit complementary strengths and weaknesses. 3D Gaussian Splatting converges quickly and carries useful geometric priors, but surface fidelity is limited by its point-like parameterization. Sparse-voxel rasterization provides continuous opacity fields and crisp geometry, but its typical uniform dense-grid initialization slows convergence and underutilizes scene structure. We combine the advantages of both by introducing a voxel initialization method that places voxels at plausible locations and with appropriate levels of detail, yielding a strong starting point for per-scene optimization. To further enhance depth consistency without blurring edges, we propose refined depth geometry supervision that converts multi-view cues into direct per-ray depth regularization. Experiments on standard benchmarks demonstrate improvements over prior methods in geometric accuracy, better fine-structure recovery, and more complete surfaces, while maintaining fast convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17720
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Advancing Structured Priors for Sparse-Voxel Surface Reconstruction
Chi, Ting-Hsun
Chen, Chu-Rong
Hsu, Chi-Tun
Lin, Hsuan-Ting
Huang, Sheng-Yu
Sun, Cheng
Wang, Yu-Chiang Frank
Computer Vision and Pattern Recognition
Reconstructing accurate surfaces with radiance fields has progressed rapidly, yet two promising explicit representations, 3D Gaussian Splatting and sparse-voxel rasterization, exhibit complementary strengths and weaknesses. 3D Gaussian Splatting converges quickly and carries useful geometric priors, but surface fidelity is limited by its point-like parameterization. Sparse-voxel rasterization provides continuous opacity fields and crisp geometry, but its typical uniform dense-grid initialization slows convergence and underutilizes scene structure. We combine the advantages of both by introducing a voxel initialization method that places voxels at plausible locations and with appropriate levels of detail, yielding a strong starting point for per-scene optimization. To further enhance depth consistency without blurring edges, we propose refined depth geometry supervision that converts multi-view cues into direct per-ray depth regularization. Experiments on standard benchmarks demonstrate improvements over prior methods in geometric accuracy, better fine-structure recovery, and more complete surfaces, while maintaining fast convergence.
title Advancing Structured Priors for Sparse-Voxel Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.17720