Google introduces URL2Video, a research prototype pipeline that automatically converts a web page into a short video.
Brief Introduction to Automatic Video creation from a Web Page
URL2Video is an AI-based tool that only requires the URL of the website to perform the task, given the content owner’s temporal and visual constraints. It extracts quality materials like texts, images, or videos and design styles, including fonts, colors, and layouts, from HTML, CSS, DOM information and organizes the assets into a relevant sequence of shots, which looks similar to the website. It then renders these to a video with a user-specified aspect ratio and duration to make a meaningful video.
Fig: By extracting the structural content and design from the input web page, URL2Video makes automatic editing decisions to present key messages in a video. It considers the temporal (e.g., the duration in seconds) and spatial (e.g., the aspect ratio) constraints of the output video defined by users.
Below is an example of converting a page that embeds multiple short video clips into a 12 seconds output video. It shows how the pipeline makes automatic editing decisions such as choosing the font, color, timing, content order, etc.
Fig: URL2Video identifies key content from our Google Search introduction page (top), including headings and video assets. It converts them into a video by considering the presentation flow, the source design and the output constraints (a 12-second landscape video; bottom).