MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Shiyao, Guédon, Antoine, Chen, Shizhe, Lepetit, Vincent
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908984538038272
author Li, Shiyao
Guédon, Antoine
Chen, Shizhe
Lepetit, Vincent
author_facet Li, Shiyao
Guédon, Antoine
Chen, Shizhe
Lepetit, Vincent
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22650
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
Li, Shiyao
Guédon, Antoine
Chen, Shizhe
Lepetit, Vincent
Computer Vision and Pattern Recognition
Robotics
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.
title MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2603.22650