Spatio-temporal video compositing

A computer program product, comprising:

• a non-transitory computer-readable medium containing computer program code that, when executed, is configured to:
• receive a first selection of pixels from a first video stream and a second selection of pixels from a second video stream, where both the first selection of pixels and the second selection of pixels indicate pixels to be included in the composite video stream;
• identify a plurality of spatiotemporal seams across the first video stream and the second video stream having a minimal visibility impact with respect to both space and time, based at least in part on the first selection of pixels and the second selection of pixels;
• and
• composite the first video stream and the second video stream to create the composite video stream, by joining frames from the first video stream and the second video stream at the identified plurality of spatiotemporal seams.

A system, comprising:

• a processor;
• and
• a memory containing a program that, when executed by the processor, performs an operation comprising:
• receiving a first selection of pixels from a first video stream and a second selection of pixels from a second video stream, where both the first selection of pixels and the second selection of pixels indicate pixels to be included in the composite video stream;
• identifying a plurality of spatiotemporal seams across the first video stream and the second video stream having a minimal visibility impact with respect to both space and time, based at least in part on the first selection of pixels and the second selection of pixels;
• and
• compositing the first video stream and the second video stream to create the composite video stream, by joining frames from the first video stream and the second video stream at the identified plurality of spatiotemporal seams.