Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
2026-05-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present AmbiSuR, a new method for creating 3D surface models from images that deals with common problems caused by ambiguous lighting and colors. They focus on a technique called Gaussian Splatting and find two types of ambiguity in how surfaces are represented. To fix this, they develop ways to both detect these ambiguities and correct them, leading to clearer and more accurate surface reconstructions. Their experiments show that AmbiSuR works better than previous methods in various difficult situations.
Surface ReconstructionDifferentiable RenderingPhotometric AmbiguityGaussian Splatting3D GeometryAmbiguity DisambiguationIntrinsic MotivationSelf-IndicationComputer Vision
Authors
Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu, Gim Hee Lee
Abstract
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/ .