European Conference on Computer Vision (ECCV) 2012

Exposure Stacks of Live Scene With Hand-held Cameras

Jun Hu Orazio Gallo Kari Pulli
Duke University Nvidia Research Nvidia Research

[PDF] [BibTex][Additional results]


Many computational photography applications require the user to take multiple pictures of the same scene with different camera settings. While this allows to capture more information about the scene than what is possible with a single image, the approach is limited by the requirement that the images be perfectly registered. In a typical scenario the camera is hand-held and is therefore prone to moving during the capture of an image burst, while the scene is likely to contain moving objects. Combining such images without careful registration introduces annoying artifacts in the final image. This paper presents a method to register exposure stacks in the presence of both camera motion and scene changes. Our approach warps and modifies the content of the images in the stack to match that of a reference image. Even in the presence of large, highly non-rigid displacements we show that the images are correctly registered to the reference. While still not suitiable for reall-time applications, our algorithm is reasonably fast. For a 1024x768 image it takes 3-4 minutes.

globally registered stack Our HDR
Globally registered stack.
Our result.
The full stack.