Paparazzo: Active Mapping of Moving 3D Objects

arXiv cs.CV / 4/22/2026

📰 NewsDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

The paper introduces a new task called “active mapping of moving objects,” targeting 3D reconstruction pipelines that typically assume static environments.
It presents Paparazzo, a learning-free method that predicts a target object’s trajectory and selects the most informative viewpoints to observe it while planning the mapping agent’s path.
The work also releases a comprehensive benchmark specifically designed to evaluate performance on this new dynamic mapping problem.
Experiments show Paparazzo improves both the completeness and accuracy of 3D reconstruction compared with multiple strong baselines, advancing dynamic scene understanding.

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/