Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
For researchers in 3D reconstruction, this work provides a robust solution to a known bottleneck (photometric ambiguity) in differentiable rendering, improving surface accuracy.
AmbiSuR addresses photometric ambiguities in Gaussian Splatting-based surface reconstruction by introducing a disambiguation constraint and an ambiguity indication module, achieving superior reconstruction quality across challenging scenarios.
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/ .