Quantcast

3D Time-Lapse Reconstruction from Internet Photos

Research paper by Ricardo Martin-Brualla, David Gallup; Steven M. Seitz

Indexed on: 24 Nov '17Published on: 01 Dec '17Published in: International journal of computer vision



Abstract

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.