A team of computer scientists from Tsinghua and Beihang Universities in China, Harvard University in the US and IDC Herzliya in Israel, have developed a new video editing tool that can generate videos from the themes of the text and has named it "Write-A-Video".
The tool helps amateurs in making good quality videos in a simple and user-friendly manner without any requirement for professional video editing and producing skills. The group of scientists presented their work at the ACM SIGGRAPH Asia, held November 17 to 20 in Brisbane, Australia.
The tool helps in telling stories much more naturally
The new methods by which this tool have been developed do not demand any video processing or editing skills like other tools require but it allows to tell the stories much more naturally. According to the researchers the tool can be used to create a video by just simply editing the text that accompanies the clip. For example, adding or deleting text, and moving sentences around convert to video-editing operations, such as finding corresponding shots, cutting and rearranging shots, and creating a final video montage result.
AAs per Professor Ariel Shamir, Dean of the Efi Arazi School of Computer Science at IDC Herzliya, the tool uses current advances in automatic video understanding and also a unique user interface which makes the video created turn out to be much more simple and natural. Ariel went on to say that with their tool, "the user provides input mostly in the form of editing of text. The tool automatically searches for semantically matching candidate shots from a video repository, and then uses an optimization method to assemble the video montage by cutting and reordering the shots automatically."
Exploring visual styles
Dr Miao Wang from Beihang University stated that the tool lets the users to explore visual styles for every scene using cinematographic idioms. While selecting the candidate shots from video repository, the aesthetic approach of the shots are also taken into consideration, choosing those that are ideally lit, that are well focused and are not blurry or unstable. "At any point, the user can render the movie and preview the video montage result with an accompanying voice-over narration," said Professor Shi-Min Hu from Tsinghua University.
The team's research shows that intelligent digital tools combining the abilities of humans and algorithms together can assist users in the creative process. "Our work demonstrates the potential of automatic visual-semantic matching in idiom-based computational editing, offering an intelligent way to make video creation more accessible to non-professionals," said Shamir.