Automated outdoor depth-map generation and alignment

Image enhancement
Synthetic depth
3D terrain
Free-form warping
Image registration
Synthetic camera

Image enhancement tasks can highly benefit from depth information, but the direct estimation of outdoor depth maps is difficult due to vast object distances. This paper presents a fully automatic framework for model-based generation of outdoor depth maps and its applications to image enhancements. We leverage 3D terrain models and camera pose estimation techniques to render approximate depth maps without resorting to manual alignment. Potential local misalignments, resulting from insufficient model details and rough registrations, are eliminated with our novel free-form warping. We first align synthetic depth edges with photo edges using the as-rigid-as-possible image registration and further refine the shape of the edges using the tight trimap-based alpha matting. The resulting synthetic depth maps are accurate, calibrated in the absolute distance. We demonstrate their benefit in image enhancement techniques including reblurring, depth-of-field simulation, haze removal, and guided texture synthesis.

Image enhancement tasks can highly benefit from depth information, but the direct estimation of outdoor depth maps is difficult due to vast object distances. This paper presents a fully automatic framework for model-based generation of outdoor depth maps and its applications to image enhancements. We leverage 3D terrain models and camera pose estimation techniques to render approximate depth maps without resorting to manual alignment. Potential local misalignments, resulting from insufficient model details and rough registrations, are eliminated with our novel free-form warping. We first align synthetic depth edges with photo edges using the as-rigid-as-possible image registration and further refine the shape of the edges using the tight trimap-based alpha matting. The resulting synthetic depth maps are accurate, calibrated in the absolute distance. We demonstrate their benefit in image enhancement techniques including reblurring, depth-of-field simulation, haze removal, and guided texture synthesis.

Our method allows to register synthetic depth maps with an outdoor photographs for subsequent editing, which has not been possible until now. This unique feature may be applied in virtual and augmented reality systems as well as in image editing software.

This work has been published as an impacted journal paper (Computers & Graphics 2018), and it is available online: https://www.sciencedirect.com/science/article/pii/S0097849318300608
Supplementary materials and a video summarizing our paper are available on the project webpage: http://cphoto.fit.vutbr.cz/depth/