Deep photo
University of Konstanz · Microsoft Research (United Kingdom) · +3 more institutions
Abstract
In this paper, we introduce a novel system for browsing, enhancing, and manipulating casual outdoor photographs by combining them with already existing georeferenced digital terrain and urban models. A simple interactive registration process is used to align a photograph with such a model. Once the photograph and the model have been registered, an abundance of information, such as depth, texture, and GIS data, becomes immediately available to our system. This information, in turn, enables a variety of operations, ranging from dehazing and relighting the photograph, to novel view synthesis, and overlaying with geographic information. We describe the implementation of a number of these applications and discuss…
Citation impact
- FWCI
- 17.04
- Percentile
- 100%
- References
- 49
Authors
8Topics & keywords
- Computer science
- Variety (cybernetics)
- Terrain
- Overlay
- Computer graphics (images)
- Process (computing)
- Computer vision
- Artificial intelligence
- Sustainable cities and communities