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

2026-04-19

AI Summary

This work addresses the limitations of traditional point cloud registration methods under conditions of low overlap and partial observability by proposing a two-stage framework that integrates geometric, color, and Gaussian-based information. The approach introduces a color-enhanced encoder to extract multi-scale geometry-color features, a Geometric-3DGS module to model local neighborhoods and construct globally invariant context, and combines LoRA-based parameter-efficient optimization, fast differentiable rendering, and a joint geometric-photometric loss function. Evaluated on the Color3DMatch and Color3DLoMatch benchmarks, the method achieves a registration recall of 99.9%, with rotation and translation errors as low as 0.013 and 0.024, respectively—demonstrating at least a two-fold improvement in accuracy over existing state-of-the-art techniques.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• point cloud registration
• color information
• low-overlap
• geometric features
• robust registration

Innovation

• Geometric-3DGS fusion
• color-enhanced registration
• two-stage point cloud registration
• LoRA optimization
• differentiable rendering