Blowing in the Wind: CycleNet for Human Cinemagraphs from Still Images
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 459-468
Abstract
Cinemagraphs are short looping videos created by adding subtle motions to a static image. This kind of media is popular and engaging. However, automatic generation of cinemagraphs is an underexplored area and current solutions require tedious low-level manual authoring by artists. In this paper, we present an automatic method that allows generating human cinemagraphs from single RGB images. We investigate the problem in the context of dressed humans under the wind. At the core of our method is a novel cyclic neural network that produces looping cinemagraphs for the target loop duration. To circumvent the problem of collecting real data, we demonstrate that it is possible, by working in the image normal space, to learn garment motion dynamics on synthetic data and generalize to real data. We evaluate our method on both synthetic and real data and demonstrate that it is possible to create compelling and plausible cinemagraphs from single RGB images.Keywords
All Related Versions
Funding Information
- icrea (PID2019-105093GB-I00)
This publication has 37 references indexed in Scilit:
- Fast computation of seamless video loopsACM Transactions on Graphics, 2015
- Intrinsic images in the wildACM Transactions on Graphics, 2014
- Automated video looping with progressive dynamismACM Transactions on Graphics, 2013
- Selectively de-animating videoACM Transactions on Graphics, 2012
- Animating Pictures of Fluid using Video ExamplesComputer Graphics Forum, 2009
- Panoramic video texturesACM Transactions on Graphics, 2005
- Animating pictures with stochastic motion texturesACM Transactions on Graphics, 2005
- Flow-based video synthesis and editingACM Transactions on Graphics, 2004
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Video textures2000