SVRecon: Sparse Voxel Rasterization for Surface Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Oh, Seunghun, Choe, Jaesung, Lee, Dongjae, Lee, Daeun, Jeong, Seunghoon, Wang, Yu-Chiang Frank, Park, Jaesik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914166566027264
author Oh, Seunghun
Choe, Jaesung
Lee, Dongjae
Lee, Daeun
Jeong, Seunghoon
Wang, Yu-Chiang Frank
Park, Jaesik
author_facet Oh, Seunghun
Choe, Jaesung
Lee, Dongjae
Lee, Daeun
Jeong, Seunghoon
Wang, Yu-Chiang Frank
Park, Jaesik
contents We extend the recently proposed sparse voxel rasterization paradigm to the task of high-fidelity surface reconstruction by integrating Signed Distance Function (SDF), named SVRecon. Unlike 3D Gaussians, sparse voxels are spatially disentangled from their neighbors and have sharp boundaries, which makes them prone to local minima during optimization. Although SDF values provide a naturally smooth and continuous geometric field, preserving this smoothness across independently parameterized sparse voxels is nontrivial. To address this challenge, we promote coherent and smooth voxel-wise structure through (1) robust geometric initialization using a visual geometry model and (2) a spatial smoothness loss that enforces coherent relationships across parent-child and sibling voxel groups. Extensive experiments across various benchmarks show that our method achieves strong reconstruction accuracy while having consistently speedy convergence. The code will be made public.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17364
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
Oh, Seunghun
Choe, Jaesung
Lee, Dongjae
Lee, Daeun
Jeong, Seunghoon
Wang, Yu-Chiang Frank
Park, Jaesik
Computer Vision and Pattern Recognition
We extend the recently proposed sparse voxel rasterization paradigm to the task of high-fidelity surface reconstruction by integrating Signed Distance Function (SDF), named SVRecon. Unlike 3D Gaussians, sparse voxels are spatially disentangled from their neighbors and have sharp boundaries, which makes them prone to local minima during optimization. Although SDF values provide a naturally smooth and continuous geometric field, preserving this smoothness across independently parameterized sparse voxels is nontrivial. To address this challenge, we promote coherent and smooth voxel-wise structure through (1) robust geometric initialization using a visual geometry model and (2) a spatial smoothness loss that enforces coherent relationships across parent-child and sibling voxel groups. Extensive experiments across various benchmarks show that our method achieves strong reconstruction accuracy while having consistently speedy convergence. The code will be made public.
title SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.17364