1Harbin Engineering University 2University of Liverpool 3ETH Zurich 4National University of Singapore 5University of Macau 6Xi’an Jiaotong-Liverpool University 7The Hong Kong University of Science and Technology (Guangzhou) 8Imperial College London 9Huazhong University of Science and Technology
Under Review
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) via fast Fourier correlation across arbitrary orientations and rejects symmetric false closures through global Sim(3) consensus. Building on these closures, directional global optimization solves a per-keyframe 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. Code and benchmark tools will be publicly released.

Swipe horizontally to inspect details
Figure 1. Collaborative panoramic Gaussian splatting SLAM with CoSphere-SLAM. Four monocular panoramic agents at top left are aligned into one 3D Gaussian map at top center with 360° rendering at top right on Scene 002. While the bottom left shows a loop closure at opposite headings, a symmetric layout, and scale drift, the bottom right compares trajectories, single-agent ATE or multi-agent joint ATE, and masked front-face PSNR across three development scenes against dashed ground truth, with RICP registering ODGS-SLAM maps via RANSAC and ICP.

Figure 2. Fraction of inter-agent meetings connected by a verified loop closure across relative agent orientations on the development set.
A monocular panorama observes the unit sphere S² without field-of-view limits. Viewing directions are therefore scale-free and shared at any heading, while discrete room symmetries and continuous radial scale remain unobservable within one view. CoSphere-SLAM resolves both ambiguities on the sphere:

Swipe horizontally to inspect the full architecture
Figure 3. Overview of CoSphere-SLAM. Each agent resamples panoramas into six cube-map faces with scale-aligned depth to track poses and build local 3D Gaussians. On the server, spherical loop closure aligns spherical feature maps over SO(3) via circular FFT and removes symmetric false closures via global Sim(3) consensus across clusters and agent loops. Directional global optimization solves a per-keyframe Sim(3) pose graph separating optical-flow directions from depth-aligned magnitudes, and omnidirectional Gaussian fusion deforms Gaussians by their keyframe similarities to refine all poses and maps along viewing rays.

Figure 4. Omnidirectional Gaussian fusion. Left: evaluating Gaussians at their maximum ray response and compositing front to back avoids polar stretch and dashed seam cuts. Right: per-keyframe Sim(3) scaling forms the merged map while random 3D rotations move poles onto the equator for 2D SSIM supervision.
Per-agent tracking and mapping. Each agent tracks six 90° cube faces sharing one optical center with a DROID-SLAM front end, aligns per-face monocular depth into one spherical depth map, and sends a compact ring descriptor with every keyframe pose, running online at 1.0 input FPS in 7.8 GiB of GPU memory.
Rendering along viewing rays. Six-face rasterization inflates cube-seam gradients to 6.0M Gaussians, whereas ray evaluation keeps 0.50M and raises development WS-PSNR from 22.80 dB to 27.18 dB.
Interactive demo. Keyframe trajectories of the four agents on the five development scenes, drawn over the merged Gaussian map of CoSphere-SLAM (Gaussian centers in their base color), with Agents 1 to 4 in orange, gunmetal, steel, and yellow as in the paper. Multi-Agent methods align all agents to the ground truth with one Sim(3), and Single-Agent methods align each agent on its own. Mean is the per-agent ATE (m) of Table 1, Joint is the error of all agents under one Sim(3), and a dagger marks a mean over the tracked agents. Drag to rotate, right-drag or Shift-drag to pan, and scroll to zoom. The ceiling cut hides the map above a height over the cameras so that the floor plan stays visible.

Swipe horizontally to inspect details
@article{shao2026cosphereslam,
title = {{CoSphere-SLAM}: Multi-Agent Panoramic {G}aussian Splatting {SLAM} with Spherical Loop Closure},
author = {Shao, Qi and Cao, Zhihao and Zhai, Shuhao and Wu, Taoyu and Li, Zhuoxiao and Nguyen, Anh and Hu, Long and Li, Xianzhi and Liang, Hong and Huang, Baoru and Li, Liang},
journal = {arXiv preprint arXiv:2611.22235},
year = {2026}
}
The supplementary material provides the following details beyond the main paper.
All hyperparameters of the panoramic agents, spherical loop closure, directional global optimization and omnidirectional Gaussian fusion, fixed across Holo360D and 360Loc.
Per-agent ATE of every method on all 50 Holo360D scenes, and estimated trajectories on four development scenes.
Single-agent tracking, joint pose-graph optimization, revisit closures, the drifted corridor branch of Scene 027, the symmetric Scenes 001 and 021, and communication and runtime.
Cube-map rig, panoramic depth prior, spherical Gaussian map, compact messages, ring descriptor, geometric verification, cluster selection, loop constraint and pose graph, loop noise model, map merging and global refinement, and loop closure thresholds.
Spherical correlation, cycle consistency, per-keyframe scale, the loop constraint, rendering along rays, and map merging.
How the multi-agent Holo360D benchmark is built from single sequences, how each baseline is run, and the protocol behind Figure 1.
Front-face rendering on the test scenes with SSIM and masked metrics, and an omnidirectional 3DGS comparison at 2048 × 1024 with multi-agent scene coverage.
Per-session ATE, joint ATE and verified cross-session closures for each building, and all multi-session baselines across the 18 day and night sessions.
One-at-a-time sweeps of the cluster radius, robust kernel and scale random-walk regularization over the 45 test scenes.
Replacing the backend with MAGS-SLAM association, SO(3) search with yaw-only search, flow directions with depth directions, and ray evaluation with projective cube-face 3DGS.
Fraction of inter-agent meetings connected by a verified closure in each relative-orientation bin, against yaw-only search and front-face matching.