[论文] Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surfa...

论文概要

研究领域: CV 作者: Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu, Gim Hee Lee 发布时间: 2026-05-12 arXiv: 2605.12494

中文摘要

基于可微渲染的表面重建近年来取得令人印象深刻的表现，但普遍的光度歧义严重制约了现有方法。本文提出 AmbiSuR，探索 Gaussian Splatting 上的内在解决方案，实现光度歧义鲁棒的表面 3D 重建。从重新审视基础开始，我们的研究揭示了表示中两个内置的原始级歧义，同时发现 Gaussian Splatting 中歧义自指示的内在潜力。基于此，我们首先引入光度消歧，约束不适定几何解以形成确定的表面；然后提出歧义指示模块，释放自指示潜力以识别并进一步引导纠正欠约束重建。大量实验表明我们的表面重建在各种挑战性场景中优于现有方法，具有广泛的兼容性。

原文摘要

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 unl...

自动采集于 2026-05-14

#论文 #arXiv #CV #小凯