Gaussian Surface Reconstruction with Adaptive Depth Supervision for Geographic Information Systems

Abstract Surface reconstruction from overlapping images supplies geometry for three-dimensional geographic information systems (GIS), but stereo depth errors can constrain the recovered surfaces. We present HelixGau, a Gaussian surface reconstruction method that filters and updates stereo depth during optimization. Local correlation with monocular depth selects pixels for supervision, while stereo estimates supply the supervised values. Rendered planes with higher photometric correlation across views provide candidates for stereo plane updates. The updated depth maps are filtered before supervision, and surfaces are extracted after optimization. On 16 BlendedMVS scenes, mean F1 is 88.64 with a standard deviation of 0.09 over four runs, compared with the highest baseline mean of 76.85. Mean F1 is 0.500 on six Tanks and Temples scenes. On the Technical University of Denmark (DTU) benchmark, overall error is 0.505 mm, compared with the lowest baseline error of 0.504 mm. Component ablations measure the separate effects of filtering and updates on the reconstructed geometry.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-11609305/v1
Primary Topic
Advanced Vision and Imaging
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Gaussian Surface Reconstruction with Adaptive Depth Supervision for Geographic Information Systems

Xiangqian Shen, Jiongming Qin, Tuo Cao, Chunxia Xiao et al.
1 links
Research Square
Advanced Vision and Imaging
preprint

Gaussian Surface Reconstruction with Adaptive Depth Supervision for Geographic Information Systems

Xiangqian Shen, Jiongming Qin, Tuo Cao, Chunxia Xiao, Yusen Wang
preprint en

Abstract

Abstract Surface reconstruction from overlapping images supplies geometry for three-dimensional geographic information systems (GIS), but stereo depth errors can constrain the recovered surfaces. We present HelixGau, a Gaussian surface reconstruction method that filters and updates stereo depth during optimization. Local correlation with monocular depth selects pixels for supervision, while stereo estimates supply the supervised values. Rendered planes with higher photometric correlation across views provide candidates for stereo plane updates. The updated depth maps are filtered before supervision, and surfaces are extracted after optimization. On 16 BlendedMVS scenes, mean F1 is 88.64 with a standard deviation of 0.09 over four runs, compared with the highest baseline mean of 76.85. Mean F1 is 0.500 on six Tanks and Temples scenes. On the Technical University of Denmark (DTU) benchmark, overall error is 0.505 mm, compared with the lowest baseline error of 0.504 mm. Component ablations measure the separate effects of filtering and updates on the reconstructed geometry.

Research Square
Chinese Academy of Sciences (CN), Wuhan University (CN)
Advanced Vision and Imaging
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon