We also evaluate the utility of our proposed macro generation workflow via a small informal lab study with professional photographers. We ask viewers to compare images generated using our content-adaptive macros with and without corrections to manually generated ground-truth images and find that they consistently rate both our automatic and corrected results as close in appearance to the ground truth. Our framework also provides interactive controls to help macro authors and users generate training demonstrations and correct errors due to incorrect labeling or poor parameter estimation. Although our approach is limited to learning manipulations where there is a direct dependency between image features and operation parameters, we show that our framework is able to learn a large class of the most commonly used manipulations using as few as 20 training demonstrations. Specifically, we use automated image labeling and machine learning techniques to learn the dependencies between image features and the parameters of each selection, brush stroke, and image processing operation in the macro. To create a content-adaptive macro, we make use of multiple training demonstrations.
We demonstrate applications of our framework to face, landscape, and global manipulations. We present a framework for generating content-adaptive macros that can transfer complex photo manipulations to new target images. Outstanding Doctoral Dissertation Award.Electronic Theater Best Student Project.All Conference-Related Electronic Media Publications.Film and Video Show & Electronic Theater Catalogs.Technical Paper Overviews: SIGGRAPH Asia.Keynote Session Overviews: SIGGRAPH Asia.Exhibitor Session Overviews: SIGGRAPH Asia.Educator’s Forum Overviews: SIGGRAPH Asia.Real-Time Live! Overviews: SIGGRAPH Asia.SIGGRAPH Artworks in the Victoria & Albert Museum.
0 kommentar(er)
