Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Jiahe, Zhang, Jiawei, Bai, Xiao, Zheng, Jin, Yu, Xiaohan, Gu, Lin, Lee, Gim Hee
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918497919959040
author Li, Jiahe
Zhang, Jiawei
Bai, Xiao
Zheng, Jin
Yu, Xiaohan
Gu, Lin
Lee, Gim Hee
author_facet Li, Jiahe
Zhang, Jiawei
Bai, Xiao
Zheng, Jin
Yu, Xiaohan
Gu, Lin
Lee, Gim Hee
contents Surface reconstruction with differentiable rendering has achieved impressive performance in recent years, yet the pervasive photometric ambiguities have strictly bottlenecked existing approaches. This paper presents AmbiSuR, a framework that explores an intrinsic solution upon Gaussian Splatting for the photometric ambiguity-robust surface 3D reconstruction with high performance. Starting by revisiting the foundation, our investigation uncovers two built-in primitive-wise ambiguities in representation, while revealing an intrinsic potential for ambiguity self-indication in Gaussian Splatting. Stemming from these, a photometric disambiguation is first introduced, constraining ill-posed geometry solution for definite surface formation. Then, we propose an ambiguity indication module that unleashes the self-indication potential to identify and further guide correcting underconstrained reconstructions. Extensive experiments demonstrate our superior surface reconstructions compared to existing methods across various challenging scenarios, excelling in broad compatibility. Project: https://fictionarry.github.io/AmbiSuR-Proj/ .
format Preprint
id arxiv_https___arxiv_org_abs_2605_12494
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
Li, Jiahe
Zhang, Jiawei
Bai, Xiao
Zheng, Jin
Yu, Xiaohan
Gu, Lin
Lee, Gim Hee
Computer Vision and Pattern Recognition
Surface reconstruction with differentiable rendering has achieved impressive performance in recent years, yet the pervasive photometric ambiguities have strictly bottlenecked existing approaches. This paper presents AmbiSuR, a framework that explores an intrinsic solution upon Gaussian Splatting for the photometric ambiguity-robust surface 3D reconstruction with high performance. Starting by revisiting the foundation, our investigation uncovers two built-in primitive-wise ambiguities in representation, while revealing an intrinsic potential for ambiguity self-indication in Gaussian Splatting. Stemming from these, a photometric disambiguation is first introduced, constraining ill-posed geometry solution for definite surface formation. Then, we propose an ambiguity indication module that unleashes the self-indication potential to identify and further guide correcting underconstrained reconstructions. Extensive experiments demonstrate our superior surface reconstructions compared to existing methods across various challenging scenarios, excelling in broad compatibility. Project: https://fictionarry.github.io/AmbiSuR-Proj/ .
title Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12494