# GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion Source: [GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion]() Collection index: [llms.txt]() Data updated: 2026-04-22T05:22:24.044Z Authors: Jiayi Tian, Haiduo Huang, Tian Xia, Wenzhe Zhao, Pengju Ren Published: 2026-04-20T02:14:41.000Z ## 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 \\textbf{Ge}ometric-3D\\textbf{GS} 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 \\textit{Registration Recall} at 99.9\\%, \\textit{Relative Rotation Error} as low as 0.013, and \\textit{Relative Translation Error} as low as 0.024, improving precision by at least a factor of 2. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Point Cloud Registration on C3DLM](): Point cloud registration; C3DLM; Registration Recall: 90.7. - [Point Cloud Registration on C3DM](): Point cloud registration; C3DM; Feature Matching Recall: 99.7. - [Point Cloud Registration on Color3DMatch (C3DM)](): Point cloud registration; Color3DMatch (C3DM); Registration Recall: 97.9. - [Point Cloud Registration on Color3DMatch (C3DM) indoor](): Point cloud registration; Color3DMatch (C3DM) indoor; Registration Recall: 97.9. - [Point Cloud Registration on Color3DLoMatch (C3DLM) indoor](): Point cloud registration; Color3DLoMatch (C3DLM) indoor; Registration Recall: 90.7. - [Point Cloud Registration on ColorKitti (test)](): Point cloud registration; ColorKitti (test); RTE (cm): 5.7. - [Point Cloud Registration on C3DM (Color3DMatch)](): Point cloud registration; C3DM (Color3DMatch); RRE (°): 1.112. - [Point Cloud Registration on C3DLM (Color3DLoMatch)](): Point cloud registration; C3DLM (Color3DLoMatch); Rotational Relative Error (°): 2.293. ## Original sources and implementation [Original paper]() [PDF]()