PhotoPath: Single Image Path Depictions from Multiple Photographs

In: Journal of WSCG (Feb. 2010), 18:1-3
 

Abstract

In this paper we present PhotoPath, an image synthesis technique that allows the visualization of paths through real world environments in a single intuitive picture. Given a series of input photographs taken with a hand-held camera along the path, our method generates an image that creates the impression of looking along the path all the way to the destination regardless of any curves or corners in the route. Rendered from a pedestrian perspective, this visualization supports intuitive wayfinding and orientation while avoiding occlusion of path segments in the image.

Our approach intentionally avoids an involved and error-prone scene reconstruction. Instead we advocate the use of planar geometry proxies estimated from the sparse point-cloud obtained with Structure-from-Motion. The proxy geometry is spatially deformed in order to align the curved path with the straight viewing direction of the synthesized view. Finally, we propose a novel image composition algorithm accommodating for parallax and occlusion artifacts due to the approximation errors of the actual scene geometry.

Keywords: image-based rendering, navigation, non-photorealistic rendering, space-deformation

Images

Download Paper

Download Paper

Bibtex

@ARTICLE{schwartz-2010-photopath,
    author = {Schwartz, Christopher and Schnabel, Ruwen and Degener, Patrick and Klein, Reinhard},
     title = {PhotoPath: Single Image Path Depictions from Multiple Photographs},
   journal = {Journal of WSCG},
    volume = {18},
    number = {1-3},
      year = {2010},
     month = feb,
  keywords = {image-based rendering, navigation, non-photorealistic rendering, space-deformation},
  abstract = {In this paper we present PhotoPath, an image synthesis technique that allows
              the visualization of paths through real world environments in a single
              intuitive picture. Given a series of input photographs taken with a hand-held
              camera along the path, our method generates an image that creates the
              impression of looking along the path all the way to the destination regardless
              of any curves or corners in the route. Rendered from a pedestrian perspective,
              this visualization supports intuitive wayfinding and orientation while avoiding
              occlusion of path segments in the image.
              
              Our approach intentionally avoids an involved and error-prone scene
              reconstruction. Instead we advocate the use of planar geometry proxies
              estimated from the sparse point-cloud obtained with Structure-from-Motion. The
              proxy geometry is spatially deformed in order to align the curved path with the
              straight viewing direction of the synthesized view. Finally, we propose a novel
              image composition algorithm accommodating for parallax and occlusion artifacts
              due to the approximation errors of the actual scene geometry.},
      issn = {1213-6972}
}