Spatiotemporal Bundle Adjustment for Dynamic 3D Reconstruction

Minh Vo, Srinivasa G. Narasimhan, Yaser Sheikh; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1710-1718

Abstract


Bundle adjustment jointly optimizes camera intrinsics and extrinsics and 3D point triangulation to reconstruct a static scene. The triangulation constraint however is invalid for moving points captured in multiple unsynchronized videos and bundle adjustment is not purposed to estimate the temporal alignment between cameras. In this paper, we present a spatiotemporal bundle adjustment approach that jointly optimizes four coupled sub-problems: estimating camera intrinsics and extrinsics, triangulating 3D static points, as well as subframe temporal alignment between cameras and estimating 3D trajectories of dynamic points. Key to our joint optimization is the careful integration of physics-based motion priors within the reconstruction pipeline, validated on a large motion capture corpus. We present an end-to-end pipeline that takes multiple uncalibrated and unsynchronized video streams and produces a dynamic reconstruction of the event. Because the videos are aligned with sub-frame precision, we reconstruct 3D trajectories of unconstrained outdoor activities at much higher temporal resolution than the input videos.

Related Material


[pdf]
[bibtex]
@InProceedings{Vo_2016_CVPR,
author = {Vo, Minh and Narasimhan, Srinivasa G. and Sheikh, Yaser},
title = {Spatiotemporal Bundle Adjustment for Dynamic 3D Reconstruction},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}