Shrinkability Maps for Content-Aware Video Resizing

A novel method is given for content-aware video resizing, i.e. targeting video to a new resolution (which may involve aspect ratio change) from the original. We precompute a per-pixel cumulative shrinkability map which takes into account both the importance of each pixel and the need for continuity in the resized result. ( If both x and y resizing are required, two separate shrinkability maps are used, otherwise one suffices). A random walk model is used for efficient offline computation of the shrinkability maps. The latter are stored with the video to create a multi-sized video, which permits arbitrary-sized new versions of the video to be later very efficiently created in real-time, e. g. by a video-on-demand server supplying video streams to multiple devices with different resolutions. These shrinkability maps are highly compressible, so the resulting multi-sized videos are typically less than three times the size of the original compressed video. A scaling function operates on the multi-sized video, to give the new pixel locations in the result, giving a high-quality content-aware resized video. Despite the great efficiency and low storage requirements for our method, we produce results of comparable quality to state-of-the-art methods for content-aware image and video resizing.