4D Primitive-Mâché: Glueing Primitives for Persistent 4D Scene Reconstruction
This work addresses the challenge of dynamic scene reconstruction for applications like replayable 3D reconstructions and object permanence, representing a novel method for a known bottleneck.
The paper tackles the problem of reconstructing complete and persistent 4D scenes from monocular RGB videos, achieving significant quantitative and qualitative improvements over existing methods on object scanning and multi-object datasets.
We present a dynamic reconstruction system that receives a casual monocular RGB video as input, and outputs a complete and persistent reconstruction of the scene. In other words, we reconstruct not only the the currently visible parts of the scene, but also all previously viewed parts, which enables replaying the complete reconstruction across all timesteps. Our method decomposes the scene into a set of rigid 3D primitives, which are assumed to be moving throughout the scene. Using estimated dense 2D correspondences, we jointly infer the rigid motion of these primitives through an optimisation pipeline, yielding a 4D reconstruction of the scene, i.e. providing 3D geometry dynamically moving through time. To achieve this, we also introduce a mechanism to extrapolate motion for objects that become invisible, employing motion-grouping techniques to maintain continuity. The resulting system enables 4D spatio-temporal awareness, offering capabilities such as replayable 3D reconstructions of articulated objects through time, multi-object scanning, and object permanence. On object scanning and multi-object datasets, our system significantly outperforms existing methods both quantitatively and qualitatively.