Research map / Point clouds / Registration and matching
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
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes GeGS-PCR, a two-stage color 3D point cloud registration method fusing geometric features with 3D Gaussian Splatting (3DGS) information, with a dedicated color encoder, for low-overlap and incomplete scenes.
Problem
Point cloud registration relying only on geometric features struggles in low-overlap and incomplete scenarios; the paper aims to exploit color information for robust, fast registration.
Approach
A two-stage pipeline that fuses geometric features, color features from a dedicated color encoder, and Gaussian (3DGS) representations to improve correspondence and registration robustness.
Experimental setup
Builds on: 3D Gaussian splatting
Closest papers by meaning
- PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry (ECCV 2022 · similarity 0.94)
- ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion (CVPR 2024 · similarity 0.91)
- ColorPCR++: Unleash the Power of Color for Point Cloud Registration Using Hypergraph Computation (TPAMI 2026 · similarity 0.90)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (AAAI 2025 · similarity 0.87)
- Generative Point Cloud Registration (ICML 2025 · similarity 0.87)
- HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
