Modelling human visual attention is of great importance in the field of computer vision and has been widely explored for 3D imaging. Yet, in the absence of ground truth data, it is unclear whether such predictions are in alignment with the actual human viewing behavior in virtual reality environments. In this study, we work towards solving this problem by conducting an eye-tracking experiment in an immersive 3D scene that offers 6 degrees of freedom. A wide range of static point cloud models is inspected by human subjects, while their gaze is captured in real-time. The visual attention information is used to extract fixation density maps, that can be further exploited for saliency modelling. To obtain high quality fixation points, we devise a scheme that utilizes every recorded gaze measurement from the two eye-cameras of our set-up. The obtained fixation density maps together with the recorded gaze and head trajectories are made publicly available, to enrich visual saliency datasets for 3D models.
Al Hirschfeld (1903Hirschfeld ( -2003 is one of the foremost representatives of a great generation of cartoon line artists. He extensively drew the American popular culture of the whole 20 th century at its peak of liveliness and pushed beyond the conventional and commercial cartoon art with his exclusive focus on the minimalistic and expressive usage of pen-and-ink lines. His works uniquely stand out as part of a larger group of 20 th century cartoonists whose economy of graphic lines frequently inspired traditional 2D animators, such as Ronald Searle and Gerald Scarfe (1936-). However, the expressiveness of their line style has not been fully exploited in 3D real-time. We observe a lack of workflow and graphical tools to create their style. Thus, this essay proposes Hirschfeld's artworks as style guides to design and develop 3D line art characters in real-time animation. An innovative workflow focusing on the artistic directed control of the selection and the thickness of lines is explored and examined. Tools for real-time line style editing are developed to assist the creation of 3D real-time line art and animation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.