MSR Symposium on Computational Photography: Session 4

Опубликовано 6 сентября 2016, 16:36

Removing Camera Shake from a Single Photograph; Aaron Hertzmann - University of Toronto: Camera shake during exposure leads to objectionable image blur and ruins many photographs. Conventional blind deconvolution methods typically assume frequency domain constraints on images, or overly simplied parametric forms for the motion path during camera shake. Real camera motions can follow convoluted paths, and a spatial domain prior can better maintain visually salient image characteristics. We introduce a method to remove the effects of camera shake from seriously blurred images. The method assumes a uniform camera blur over the image, negligible in-plane camera rotation, and no blur due to moving objects in the scene. The user must specify an image region without saturation effects. I'll discuss issues in this blind deconvolution problem, and show results for a variety of digital photographs. Joint work with Rob Fergus, Barun Singh, Sam Roweis, and Bill Freeman. Object Movies, Photosynth, and other Cool Stuff; Noah Snavely, Drew Steedly - Microsoft Research: Photo Tourism and Photosynth have generated a lot of excitement as a new way to interactively visualize and navigate a collection of photographs situated in three dimensions. In this talk, we present some recent developments in our research. First, we show how by interactively manipulating viewpoints while automatically selecting the next image, we can achieve the fluidity of control and three-dimensionality inherent in *object movies*. Second, we show how three-dimensional models can be reconstructed from large uncontrolled collections of images. Finally, we discuss different approaches for dealing with large sets of data. We also present some recently reconstructed models from Korea and England.