Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene

TL;DR

This paper introduces a unified method for dense 3D reconstruction of complex dynamic scenes from monocular images, modeling scenes as assemblies of rigid planar segments to improve accuracy and address scale ambiguity.

Contribution

The authors propose a novel approach that models dynamic scenes as piecewise planar structures with local rigid motions, simplifying the reconstruction process.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively addresses scale ambiguity in structure-from-motion.

Demonstrates robustness on complex dynamic scenes.

Abstract

This work addresses the task of dense 3D reconstruction of a complex dynamic scene from images. The prevailing idea to solve this task is composed of a sequence of steps and is dependent on the success of several pipelines in its execution. To overcome such limitations with the existing algorithm, we propose a unified approach to solve this problem. We assume that a dynamic scene can be approximated by numerous piecewise planar surfaces, where each planar surface enjoys its own rigid motion, and the global change in the scene between two frames is as-rigid-as-possible (ARAP). Consequently, our model of a dynamic scene reduces to a soup of planar structures and rigid motion of these local planar structures. Using planar over-segmentation of the scene, we reduce this task to solving a "3D jigsaw puzzle" problem. Hence, the task boils down to correctly assemble each rigid piece to construct a 3D shape that complies with the geometry of the scene under the ARAP assumption. Further, we show that our approach provides an effective solution to the inherent scale-ambiguity in structure-from-motion under perspective projection. We provide extensive experimental results and evaluation on several benchmark datasets. Quantitative comparison with competing approaches shows state-of-the-art performance.