GS-I 3 : Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images

3D Gaussian Splatting (3DGS) has gained significant attention in the field of surface reconstruction due to its impressive geometric quality and computational efficiency. While recent relevant advancements in novel view synthesis under inconsistent illumination using 3DGS have shown promise, the challenge of robust surface reconstruction under such conditions is still being explored. To address this challenge, we proposed GS-I3. Specifically, to mitigate 3D Gaussian optimization bias caused by underexposed regions in single-view images, GS-I3introduces an adaptive illumination adjustment framework. Furthermore, inconsistent lighting across multiview images, resulting from variations in camera settings and complex scene illumination, often leads to geometric constraint mismatches and deviations in the reconstructed surface. To overcome this, GS-I3proposes a normal compensation mechanism that integrates reference normals extracted from single-view images with normals computed from multiview observations to effectively constrain geometric inconsistencies. Extensive experimental evaluations demonstrate that GS-I3can achieve robust and accurate surface reconstruction across complex illumination scenarios, highlighting its effectiveness and versatility in this critical challenge. The code is available: https://tfwang-9527.github.io/GS-I3/