Given an Internet photo collection of a landmark, we compute a 3D time-lapse video sequence where a virtual camera moves continuously in time and space. While previous work assumed a static camera, the addition of camera motion during the time-lapse creates a very compelling impression of parallax. Achieving this goal, however, requires addressing multiple technical challenges, including solving for time-varying depth maps, regularizing 3D point color profiles over time, and reconstructing high quality, hole-free images at every frame from the projected profiles. Our results show photorealistic time-lapses of skylines and natural scenes over many years, with dramatic parallax effects.
@article{arxiv.1511.03019,
title = {3D Time-lapse Reconstruction from Internet Photos},
author = {Ricardo Martin-Brualla and David Gallup and Steven M. Seitz},
journal= {arXiv preprint arXiv:1511.03019},
year = {2020}
}
Comments
To appear in ICCV'15. Supplementary video at: http://grail.cs.washington.edu/projects/timelapse3d/