Learning to Factorize and Relight a City
| Autor: | Andrew Liu, Alexei A. Efros, Shiry Ginosar, Tinghui Zhou, Noah Snavely |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science SIGNAL (programming language) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology Factorization 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Scale (map) ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585471 ECCV (4) |
| DOI: | 10.1007/978-3-030-58548-8_32 |
| Popis: | We propose a learning-based framework for disentangling outdoor scenes into temporally-varying illumination and permanent scene factors. Inspired by the classic intrinsic image decomposition, our learning signal builds upon two insights: 1) combining the disentangled factors should reconstruct the original image, and 2) the permanent factors should stay constant across multiple temporal samples of the same scene. To facilitate training, we assemble a city-scale dataset of outdoor timelapse imagery from Google Street View, where the same locations are captured repeatedly through time. This data represents an unprecedented scale of spatio-temporal outdoor imagery. We show that our learned disentangled factors can be used to manipulate novel images in realistic ways, such as changing lighting effects and scene geometry. Please visit http://factorize-a-city.github.io/ for animated results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|