Active mapping aims to determine how an agent should move to efficiently reconstruct unknown environments. Most existing approaches rely on greedy next-best-view prediction, resulting in inefficient exploration and incomplete reconstruction. To address this, we introduce MAGICIAN, a novel long-term planning framework that maximizes accumulated surface coverage gain through Imagined Gaussians, a scene representation based on 3D Gaussian Splatting, derived from a pre-trained occupancy network with strong structural priors. This representation enables efficient coverage gain computation for any novel viewpoint via fast volumetric rendering, allowing its integration into a tree-search algorithm for long-horizon planning. We update Imagined Gaussians and refine the trajectory in a closed loop. Our method achieves state-of-the-art performance across indoor and outdoor benchmarks with varying action spaces, highlighting the advantage of long-term planning in active mapping.
@article{arxiv.2603.22650,
title = {MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping},
author = {Shiyao Li and Antoine Guédon and Shizhe Chen and Vincent Lepetit},
journal= {arXiv preprint arXiv:2603.22650},
year = {2026}
}
Comments
Accepted at CVPR 2026 (Oral). Project webpage: https://shiyao-li.github.io/magician/