Analysis and transfer of photographic viewpoint and appearance

Abstract

To make a compelling photograph, photographers need to carefully choose the subject and composition of a picture, to select the right lens and viewpoint, and to make great efforts with lighting and post-processing to arrange the tones and contrast. Unfortunately, such painstaking work and advanced skill is out of reach for casual photographers. In addition, for professional photographers, it is important to improve workflow efficiency. The goal of our work is to allow users to achieve a faithful viewpoint for rephotography and a particular appearance with ease and speed. To this end, we analyze and transfer properties of a model photo to a new photo. In particular, we transfer the viewpoint of a reference photo to enable rephotography. In addition, we transfer photographic appearance from a model photo to a new input photo. In this thesis,we present two contributions that transfer photographic view and look using model photographs and one contribution that magnifies existing defocus given a single photo. First, we address the challenge of viewpoint matching for rephotography. Our interactive, computer-vision-based technique helps users match the viewpoint of a reference photograph at capture time. Next, we focus on the tonal aspects of photographic look using post-processing. Users just need to provide a pair of photos, an input and a model, and our technique automatically transfers the look from the model to the input. Finally, we magnify defocus given a single image. We analyze the existing defocus in the input image and increase the amount of defocus present in out-of focus regions.

(cont.) Our computational techniques increase users' performance and efficiency by analyzing and transferring the photographic characteristics of model photographs. We envision that this work will enable cameras and post-processing to embed more computation with a simple and intuitive interaction.