Search papers, labs, and topics across Lattice.
This paper introduces COLMAR, a cooperative view policy learning framework designed to enhance multi-agent active 3D reconstruction by optimizing viewpoint selection under limited sensing budgets. By formulating viewpoint allocation as a shared policy optimization with a reconstruction-aware objective, COLMAR effectively reduces inefficiencies like redundant observations and promotes team-level discovery. Experimental results on GLEAM and Replica show that COLMAR achieves up to 54% higher reconstruction accuracy and 49% greater coverage compared to heuristic and non-cooperative approaches.
COLMAR boosts multi-agent 3D reconstruction accuracy by over 50% through smarter, cooperative viewpoint selection.
Active 3D reconstruction requires selecting informative viewpoints under limited sensing budgets. In multi-agent settings, coordination inefficiencies such as redundant observations and spatial clustering can significantly reduce reconstruction quality. We present COLMAR, a cooperative view policy learning framework for multi-agent active 3D reconstruction. COLMAR formulates viewpoint allocation as a shared policy optimization over map-centric observations and introduces a reconstruction-aware objective that promotes overlap-aware coverage, team-level discovery, and collision-safe exploration. Dense feedback derived from incremental reconstruction updates aligns exploration behavior with downstream geometric quality. The policy is trained using parameter-sharing Proximal Policy Optimization (PPO) with independent per-agent action selection at deployment, conditioned on a fused team map and without inter-agent message passing for decision making. Selected viewpoints are then reconstructed with 3D Gaussian Splatting (3DGS) for high-fidelity photometric evaluation. Experiments on GLEAM and Replica demonstrate consistent improvements over heuristic and non-cooperative baselines, achieving up to 54% higher reconstruction accuracy and 49% greater coverage under matched sensing budgets.
