Paparazzo: Active Mapping of Moving 3D Objects

TL;DR

Paparazzo introduces a learning-free method for active mapping of moving objects, enabling improved 3D reconstruction in dynamic scenes by planning trajectories and viewpoints.

Contribution

It proposes a novel task and provides a comprehensive benchmark for active mapping of moving objects, with a new approach that predicts trajectories and selects informative viewpoints.

Findings

Significantly improves 3D reconstruction completeness.

Enhances accuracy in dynamic scene understanding.

Outperforms several strong baselines.

Abstract

Current 3D mapping pipelines generally assume static environments, which limits their ability to accurately capture and reconstruct moving objects. To address this limitation, we introduce the novel task of active mapping of moving objects, in which a mapping agent must plan its trajectory while compensating for the object's motion. Our approach, Paparazzo, provides a learning-free solution that robustly predicts the target's trajectory and identifies the most informative viewpoints from which to observe it, to plan its own path. We also contribute a comprehensive benchmark designed for this new task. Through extensive experiments, we show that Paparazzo significantly improves 3D reconstruction completeness and accuracy compared to several strong baselines, marking an important step toward dynamic scene understanding. Project page: https://davidea97.github.io/paparazzo-page/