Turning an Urban Scene Video into a Cinemagraph

Abstract

This paper proposes an algorithm that turns a regular video capturing urban scenes into a high-quality endless animation, known as a Cinemagraph. The creation of a Cinemagraph usually requires a static camera in a carefully configured scene. The task becomes challenging for a regular video with a moving camera and objects. Our approach first warps an input video into the viewpoint of a reference camera. Based on the warped video, we propose effective temporal analysis algorithms to detect regions with static geometry and dynamic appearance, where geometric modeling is reliable and visually attractive animations can be created. Lastly, the algorithm applies a sequence of video processing techniques to produce a Cinemagraph movie. We have tested the proposed approach on numerous challenging real scenes. To our knowledge, this work is the first to automatically generate Cinemagraph animations from regular movies in the wild.

Analysis and Simulation of Dynamic Vision in the City

“…Applying these methods also required sophisticated research backgrounds that ordinary architectural designers do not possess. 2018) or converting urban scene videos into animations of graphics codes (Yan, Liu, and Furukawa 2016) Recently, growing studies in dynamic visualization have exhibited practical tools that simulate the dynamic visual implications of designed environments in digital space (Stamps 2016, Mullins 2006. Integrating computer-aided cinematic analysis with the latest real-time 3D simulation technologies, the proposed Dynamic Visual Research and Design Protocol can accurately simulate end-users' dynamic vision for straightforward evaluation of alternate design proposals, helping to disseminate dynamic visual research knowledge to planning or architectural professionals.…”

Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning

“…More recently, Sevilla-Lara et al [30] use nonrigid morphing to create a video-loop for the case of videos having a contiguous foreground that can be segmented from its background. Yan et al [38] create a cinemagraph from a video (captured with a moving camera) by warping to a reference viewpoint and detecting looping regions as those with static geometry and dynamic appearance.…”