cs.CVNov 17, 2026

CoSphere-SLAM: Multi-Agent Panoramic Gaussian Splatting SLAM with Spherical Loop Closure

Authors: Qi Shao, Zhihao Cao, Shuhao Zhai, Taoyu Wu, Zhuoxiao Li, Anh Nguyen, Long Hu, Xianzhi Li, 

Organizations: Harbin Engineering University, Harbin, China · the University of Liverpool, Liverpool, UK · ETH Zurich, Zurich, Switzerland · the National University of Singapore, Singapore · 

Abstract

Dense collaborative mapping is essential for search and rescue, building inspection, and warehouse automation, where panoramic cameras capture the entire surroundings in a single frame. Unlike pinhole agents that share views only at similar headings, panoramic agents observe overlapping scenes at any 3D orientation, yet searching full rotations also produces mutually consistent false loop closures across distinct symmetric rooms. Moreover, continuous monocular scale drift splits rigidly merged maps at revisited surfaces, while depth noise at short baselines distorts loop translation directions. To address these challenges, we propose CoSphere-SLAM, the first multi-agent Gaussian splatting SLAM framework for panoramic cameras, whose spherical loop closure aligns spherical features over SO(3)\mathrm{SO}(3) via fast Fourier correlation across arbitrary orientations and rejects symmetric false closures through global Sim(3)\mathrm{Sim}(3) consensus. Building on these closures, directional global optimization solves a per-keyframe Sim(3)\mathrm{Sim}(3) pose graph with log-scale regularization to correct scale drift while separating optical-flow translation directions from depth-based magnitudes. Finally, omnidirectional Gaussian fusion transforms each Gaussian with its keyframe similarity and renders Gaussians at their maximum ray response to jointly refine poses and maps. Experiments on indoor and cross-session multi-agent panoramic benchmarks demonstrate that CoSphere-SLAM achieves state-of-the-art trajectory accuracy and rendering quality among single-agent and multi-agent methods. Project website: https://cosphere-slam.github.io.

Figures & tables

Explore similar work

CardsList
  1. MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction

    May 11, 2026Zhihao Cao, Qi Shao, Shuhao Zhai +4Simultaneous Localization and Mapping3D Gaussian Splatting

  2. Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM

    Apr 1, 2026Monica M. Q. Li, Pierre-Yves Lajoie, Jialiang Liu +1Multi-Robot SLAMSimultaneous Localization and Mapping

  3. CoMo3R-SLAM: Collaborative Monocular Dense SLAM with Learned 3D Reconstruction Priors for Outdoor Multi-Agent Systems

    May 28, 2026Zhihao Cao, Qi Shao, Shuhao Zhai +4Simultaneous Localization and MappingMulti-Robot Systems