GeGS-PCR: Fast and Robust Color 3D Point Cloud Registration with Two-Stage Geometric-3DGS Fusion

Jiayi Tian, Haiduo Huang, Tian Xia, Wenzhe zhao, Pengju Ren

Keywords: Point Cloud Registration; Geometric-Color Fusion; Geometric-3DGS; Color Encoding; LORA; Differentiable Rendering; Photometric Loss; Low Overlap Scenarios; Robust Registration; Multi-Stage; 3D Point Cloud Processing;

TL;DR: We propose GeGs-PCR, a two-stage point cloud registration method that integrates geometric, color, and Gaussian information, achieving robust performance and state-of-the-art results even in low-overlap scenarios.

Abstract: We address the challenge of point cloud registration using color information, where traditional methods relying solely on geometric features often struggle in low-overlap and incomplete scenarios. To overcome these limitations, we propose GeGS-PCR, a novel two-stage method that combines geometric, color, and Gaussian information for robust registration. Our approach incorporates a dedicated color encoder that enhances color features by extracting multi-level geometric and color data from the original point cloud. We introduce the Geometric-3DGS module, which encodes the local neighborhood information of colored superpoints to ensure a globally invariant geometric-color context. Leveraging LORA optimization, we maintain high performance while preserving the expressiveness of 3DGS. Additionally, fast differentiable rendering is utilized to refine the registration process, leading to improved convergence. To further enhance performance, we propose a joint photometric loss that exploits both geometric and color features. This enables strong performance in challenging conditions with extremely low point cloud overlap. We validate our method by colorizing the Kitti dataset as ColorKitti and testing on both Color3DMatch and Color3DLoMatch datasets. Our method achieves state-of-the-art performance with Registration Recall at 99.9%, Relative Rotation Error as low as 0.013, and Relative Translation Error as low as 0.024, improving precision by at least a factor of 2.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 2488