Abstract
Recently, there have been several attempts at creating ?video textures?, that is, synthesising new (potentially infinitely long) video clips
based on existing ones. One method for achieving this is to transform each frame of the video into an eigenspace using Principal Components
Analysis so that the original sequence can be viewed as a signature through a low-dimensional space. A new sequence can be generated by
moving through this space and creating ?similar? signatures. These signatures may be derived using an auto-regressive process (ARP). Such
an ARP assumes that the signature has Gaussian statistics. For many sequences this assumption is valid, however, some sequences are
strongly non-linearly correlated, in which case their statistical properties are non-Gaussian. We examine two methods by which such nonlinearities
may be overcome. The first is by modelling the non-linearity automatically using a spline, and the second using a combined
appearance model. New video sequences created using these approaches contain images never present in the original sequence and appear
very convincing.
Translated title of the contribution | Practical generation of video textures using the auto-regressive process |
---|---|
Original language | English |
Pages (from-to) | 819 - 827 |
Number of pages | 9 |
Journal | Image and Vision Computing |
Volume | 22 (10) |
DOIs | |
Publication status | Published - 1 Sept 2004 |