期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 43, 期 5, 页码 1705-1717出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2955131
关键词
Three-dimensional displays; Dynamics; Image reconstruction; Heuristic algorithms; Cameras; Motion segmentation; Surface reconstruction; Dense 3D reconstruction; perspective camera; as-rigid-as-possible; relative scale ambiguity; structure from motion
资金
- Australia Research Council ARC Centre of Excellence for Robotics Vision [CE140100016]
- ARC-LIEF [190100080]
- Natural Science Foundation of China [61871325, 61420106007, 61671387]
- New Generation of Artificial Intelligence major project [2018AAA0102800]
- ARC [DP 190102261, DE140100180]
- NVIDIA Corporation
This work proposes a unified approach to solve the task of dense 3D reconstruction of a complex dynamic scene from images, by modeling the dynamic scene as a combination of piecewise planar surfaces and local rigid motion, effectively simplifying the task and achieving state-of-the-art performance.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据