Using Computer Vision for Graphics

Опубликовано 12 августа 2016, 0:51

Creating compelling-looking content using conventional graphics techniques is often laborious and requires significant artistry and experience. Over the past few years, I have been looking into how this content-creation process can be simplified through using computer vision techniques. In this talk, I will describe a variety of projects undertaken with this goal in mind, discussing how computer vision techniques can be used to simplify animations of Chinese paintings by analyzing brush strokes; to generate free-viewpoint videos from a small number of cameras; to produce 3-D models of plants and trees from images; and to personalize automatic enhancements of photographs.