实时多相机3D重建中自校准点云融合方法
SPARK: Scalable Real-Time Point Cloud Aggregation with Multi-View Self-Calibration
- 通过多视角先验和时空一致性实现在线自标定
- 帧级融合避免累积误差，支持大规模相机系统线性扩展
- 在真实场景中提升精度与稳定性，适合动态环境应用
实时多相机3D重建对三维感知、沉浸式交互和机器人技术至关重要。现有方法在多视角融合、相机外参不确定性以及大规模相机部署的可扩展性方面存在瓶颈。本文提出SPARK，一种自校准的实时多相机点云重建框架，联合处理点云融合与外参不确定性。SPARK包含：(1) 基于多视角先验并强制跨视角与时间一致性的几何感知在线外参估计模块，实现稳定自校准；(2) 基于置信度的点云融合策略，建模像素与点级深度可靠性及可见性，抑制噪声与视图依赖不一致。通过逐帧融合而非累积，SPARK在动态场景中生成稳定点云，且计算复杂度随相机数量线性增长。在真实多相机系统上的大量实验表明，SPARK在外参精度、几何一致性、时间稳定性及实时性能上均优于现有方法，验证了其在大规模多相机3D重建中的有效性与可扩展性。
原文摘要 · Abstract (English)
Real-time multi-camera 3D reconstruction is crucial for 3D perception, immersive interaction, and robotics. Existing methods struggle with multi-view fusion, camera extrinsic uncertainty, and scalability for large camera setups. We propose SPARK, a self-calibrating real-time multi-camera point cloud reconstruction framework that jointly handles point cloud fusion and extrinsic uncertainty. SPARK consists of: (1) a geometry-aware online extrinsic estimation module leveraging multi-view priors and enforcing cross-view and temporal consistency for stable self-calibration, and (2) a confidence-driven point cloud fusion strategy modeling depth reliability and visibility at pixel and point levels to suppress noise and view-dependent inconsistencies. By performing frame-wise fusion without accumulation, SPARK produces stable point clouds in dynamic scenes while scaling linearly with the number of cameras. Extensive experiments on real-world multi-camera systems show that SPARK outperforms existing approaches in extrinsic accuracy, geometric consistency, temporal stability, and real-time performance, demonstrating its effectiveness and scalability for large-scale multi-camera 3D reconstruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。