Dynamic audio-responsive visuals generated with our music visualization system.

Figure 1: EnVisualAIzer Prototype User Interface for Exploring AI-Generated Environments, showing Previs Camera, Character and Note Placement Options, and Saved Scenes.

Figure 1: The Drawing-in-Steps workflow comprises several stages.From a simple scribble (left) to added details, to a colorized image, to a fully refined image (right).

The integration of artificial intelligence (AI) into creative domains is increasing, presenting both challenges and opportunities. In screenwriting, personal artistic expression is a fundamental aspect of the creator’s identity and work. The current use of AI in such creative processes can sometimes overshadow the creator’s vision and lead to a reduced sense of ownership over the final product. We introduce wr-AI-ter, an interactive application consisting of four basic stages: Ideation, Structure, Refinement, and Export. While some related work focuses on experts The application is intended to aid users with varying levels of screenwriting proficiency in generating screenplays using artificial intelligence, while preserving their sense of authorship. We conducted a user study with 23 participants, who had different expertise (screenwriting, documentary filmmaking, and VFX artistry). The results indicate that AI has the potential to accelerate the screenwriting process and improve the quality of scripts without compromising the sense of ownership.

Gaze and attention guiding for application in Cinematic Virtual Reality (CVR) has been a research topic with many contributions in recent years. One promising approach coming out of this research, are hints or cues that are placed within the context of the scene that is currently being viewed in VR. These hints are called “diegetic cues”. However, this approach, as many others, does not account for the possibility of interaction that modern VR technology brings with it. These interactions have the potential to move the viewer from a position of “impartial bystander” to one of “active participant” opening new possibilities for telling stories of various nature (e.g., fictional, or historical). This work, is the attempt to apply research from the field of attention guiding using diegetic cues to an interactive and narrative VR experience that was created using the Unreal Engine and newest VR-Technology. It was also attempted to use an alternative approach to narrative theory than the one being used in traditional filmmaking to explore the possibility of interactive storytelling. As a result, strong indications were found that the two diegetic cues that were implemented successfully enhance the experience of VR users in the interactive environment. The reception of the employed narrative approach also was generally positive.

This paper describes the impact of different camera distances in cinematic virtual reality. For our findings, we took a closer look at proxemics, the study on how humans behave regarding space and distances. We explored the four proxemics distances (intimate, personal, social, public) and adapted them to camera distances in cinematic virtual reality. For the user study, a stereoscopic movie with a speaking person was produced for four different distances. The results show that different distances cause different feelings in viewers similar to shot sizes in traditional movies. In our scenario - a person in a museum is speaking about an exhibit - the personal distance was preferred by the participants. As an outcome of this work, the proxemics distances were put in relation to well-known shot sizes used in traditional filmmaking.

For watching omnidirectional movies via HMD, turning the head is the most relevant and natural input technique to choose the visible part of the movie. However, there is a need for additional interactivity in cinematic virtual reality (CVR), e.g. for navigating the movie, for nonlinear story lines or for communication with other viewers watching a movie together. The input device should not disturb the viewing experience and the viewer should not be primarily aware of it. We present a design space based on numerous methods in literature and our own experiences. As a result of the design space we describe interaction techniques which meet the challenges of cinematic virtual reality. For doing this, various dimensions of the design space will be combined. The most promising method, eye-based head gestures, is described in more detail and was implemented for CVR. The conducted user study will be analyzed in future work.

This paper describes aspects which are important for camera positioning in cinematic virtual reality. For our findings, we took a closer look at proxemics, the study on how humans behave in regard to space and distances. We explored well-known shot sizes used in traditional filmmaking and put them in relation to proxemics distances. The results were adapted to camera distances in cinematic virtual reality.

Cinematic Virtual Reality has been increasing in popularity over the last years. Watching 360° movies with head mounted displays, viewers can freely choose the direction of view, and thus the visible section of the movie. In order to explore the viewers' behavior, methods are needed for collecting and analyzing data. In our experiments we compare the viewing behavior for movies with spatial and non-spatial sound and tracked the head movements of the participants. This work-in-progress describes two approaches of spatial statistics - analysis of Space Time Cubes and Getis Ord Gi* statistic - for analyzing head tracking data.

In this work, we show how the use of flickering in Cinematic Virtual Reality (CVR) content can not only guide the user's attention, but also significantly improve recall of details. The findings are particularly useful for practitioners who generate educational and corporate training content, as well as for directors of CVR videos who want to draw the user's attention to certain details in movies or virtual tours. We report on a between-subjects user study, in which we experimented with flickering methods to increase user's recall of certain details in CVR videos. Participants had to report details of objects on which the method was applied. In our experiments, the intensive flicker improved the recall of details significantly. We discuss how the studied methods can improve recall of details in different use cases.

Cinematic Virtual Reality has been increasing in popularity over the last years. Watching omnidirectional movies with head mounted displays, viewers can freely choose the direction of view, and thus the visible section of the movie. In order to explore the users' viewing behavior, methods are needed for collecting and analyzing data. We developed an analyzing tool, the CVR-Analyzer, which can be used for inspecting head pose and eye tracking data of viewers experiencing CVR movies. The visualized data are displayed on a flattened projection of the movie as flexibly controlled augmenting annotations, such as tracks or heatmaps, synchronously with the time code of the movie and allow inspecting and comparing the users' viewing behavior in different use cases.

Watching a 360° movie with Head Mounted Displays (HMDs) the viewer feels to be inside the movie and can experience it in an immersive way. The head of the viewer is exactly in the same place as the camera was when the scene was recorded. Viewing a movie by HMDs from the perspective of the camera can raise some challenges, e.g. heights of well-known objects can irritate the viewer in the case the camera height does not correspond to the physical eye height. The aim of this work is to study how the position of the camera influences presence, sickness and the user experience of the viewer. For that we considered several watching postures as well as various camera heights. The results of our experiments suggest that differences between camera and eye heights are more accepted, if the camera position is lower than the viewer's own eye height. Additionally, sitting postures are preferred and can be adapted easier than standing postures. These results can be applied to improve guidelines for 360° filmmakers.

Cinematic Virtual Reality has been increasing in popularity in the last years. Watching 360° movies with a Head Mounted Display, the viewer can freely choose the direction of view, and thus the visible section of the movie. We explored three cinematic methods of guiding the viewers' attention: lights, sounds, and movements. For that, we developed a measurement technique to obtain heat maps of viewing directions and applied statistical analysis methods for spatial data. The results of our work show that the attention of the viewer can be directed by sound and movements. New sound induces the viewer to search for the source of the sound, not all participants paid attention to the direction of the sound. In our experiments, lights without movements did not draw more attention than other objects. However, a moving light cone changed the viewing direction considerably.