collaborators

5 papers

cs.CV2026

Paparazzo: Active Mapping of Moving 3D Objects

Davide Allegro, Shiyao Li, Stefano Ghidoni +1

Current 3D mapping pipelines generally assume static environments, which limits their ability to accurately capture and reconstruct moving objects. To address this limitation, we i…

cs.CV2026

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

Shiyao Li, Antoine Guédon, Shizhe Chen +1

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, result…

cs.CV2026

sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only

Arslan Artykov, Tom Ravaud, Corentin Sautier +1

Understanding articulated objects from monocular video is a crucial yet challenging task in robotics and digital twin creation. Existing methods often rely on complex multi-view se…

cs.CV2025

Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline

Corentin Sautier, Gilles Puy, Alexandre Boulch +2

Panoptic segmentation of LiDAR point clouds is fundamental to outdoor scene understanding, with autonomous driving being a primary application. While state-of-the-art approaches ty…

cs.CV2025

NextBestPath: Efficient 3D Mapping of Unseen Environments

Shiyao Li, Antoine Guédon, Clémentin Boittiaux +2

This work addresses the problem of active 3D mapping, where an agent must find an efficient trajectory to exhaustively reconstruct a new scene. Previous approaches mainly predict t…