The collaboration between creatives and domain architects is crucial for bringing virtual characters to life. The choice of text as an input was particularly favourable as the teachers did not have to learn a new and often intimidating user interface for design software, making our system intuitive and easy to learn. The teachers could make their own narrated, animated video lessons on the knee and their limited experience in animation or video editing did not hold them back.
#Disney movie scripts pdf software
In the final part of the thesis, we present the results of our evaluation of the software done with four anatomy professors. Our system reads the script, and the resulting animation is played in a Unity player. The users have to write scripts in ASL in which they list all the parts that they want to show in the video and outline the directions for the camera movements and animation of the elements seen. This domain-specific language forms the basis of input for our authoring system. In the second part of the thesis, we present the anatomical specialisation of this language called the Anatomy Storyboard Language (ASL). This Prose Storyboard Language (PSL) is developed for broader use in film direction and analysis. This language is both human and machine-readable, and it allows us to annotate the video in text form. We first present a formal language to describe all the visual elements in a video.
In this thesis, we present a Text-to-movie authoring system for anatomy professors. But the issue of developing an easy to use software that enables teachers to create their own lessons without the need for design experts is ongoing. Multimedia methods such as animated videos and 3D anatomical models are popular to visualise the human body. One of the significant challenges faced in anatomy pedagogy is presenting complex three-dimensional body parts in classes. It is introduced very early in the curriculum, and the student is required to retain this knowledge throughout their practice. Our sentence simplification module outperforms existing systems in terms of BLEU and SARI metrics.We further evaluated our system via a user study: 68 % participants believe that our system generates reasonable animation from input screenplays.Īnatomy is one of the most essential yet challenging subjects in medical education. Information extracted from the simplified sentences is used to generate a rough storyboard and video depicting the text. We develop a set of linguistic transformation rules that simplify complex sentences. Building on an existing animation generation system for screenwriting, we create a robust NLP pipeline to extract information from screenplays and map them to the system's knowledge base. We achieve this by introducing a text simplification step into the process. In this paper, we develop a text-to-animation system which is capable of handling complex sentences. Existing text-to-animation systems can handle only very simple sentences, which limits their applications.
However, translating natural language text into animation is a challenging task. movie script writing, instructional videos, and public safety. Automatically generating animation from natural language text finds application in a number of areas e.g.