GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting

TL;DR

This paper introduces GS-Octree, a novel method combining octree-based implicit surface representations with Gaussian splatting to improve object-level 3D reconstruction accuracy under strong lighting conditions.

Contribution

It presents a four-stage approach that integrates SDFs and 3D Gaussians within an octree structure for enhanced geometric detail recovery.

Findings

Reconstructs more accurate geometry in challenging lighting conditions.

Effectively captures fine geometric details with improved SDF refinement.

Outperforms existing methods in geometry accuracy under strong lighting.

Abstract

The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasterization effectively reduces computational demands for rendering, it often struggles to accurately reconstruct the geometry of the target object, especially under strong lighting. To address this challenge, we introduce a novel approach that combines octree-based implicit surface representations with Gaussian splatting. Our method consists of four stages. Initially, it reconstructs a signed distance field (SDF) and a radiance field through volume rendering, encoding them in a low-resolution octree. The initial SDF represents the coarse geometry of the target object. Subsequently, it introduces 3D Gaussians as additional degrees of freedom, which are guided by the SDF. In the third stage, the optimized Gaussians further improve the accuracy of the SDF, allowing it to recover finer geometric details compared to the initial SDF obtained in the first stage. Finally, it adopts the refined SDF to further optimize the 3D Gaussians via splatting, eliminating those that contribute little to visual appearance. Experimental results show that our method, which leverages the distribution of 3D Gaussians with SDFs, reconstructs more accurate geometry, particularly in images with specular highlights caused by strong lighting.