Deblurring Shaken and Partially Saturated Images

Oliver Whyte (1, 2) , Josef Sivic (1, 2) , Andrew Zisserman (1, 2, 3)

1 LIENS - Laboratoire d'informatique de l'école normale supérieure
2 WILLOW - Models of visual object recognition and scene understanding
3 VGG - Visual Geometry Group

We address the problem of deblurring images degraded by camera shake blur and saturated or over-exposed pix- els. Saturated pixels are a problem for existing non-blind deblurring algorithms because they violate the assumption that the image formation process is linear, and often cause significant artifacts in deblurred outputs. We propose a for- ward model that includes sensor saturation, and use it to derive a deblurring algorithm properly treating saturated pixels. By using this forward model and reasoning about the causes of artifacts in the deblurred results, we obtain significantly better results than existing deblurring algorithms. Further we propose an efficient approximation of the forward model leading to a significant speed-up.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Oliver Whyte, Josef Sivic, Andrew Zisserman. Deblurring Shaken and Partially Saturated Images. IEEE Workshop on Color and Photometry in Computer Vision, 2011, Barcelona, Spain. ⟨hal-01053886⟩