Blue noise mask for video sampling

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

• receive a video comprising a sequence of frames;
• access a three-dimensional mask that specifies pixel-sampling locations, the three-dimensional mask having (1) a first dimension and a second dimension corresponding to a spatial domain and (2) a third dimension corresponding to a temporal domain, wherein a blue noise property is present in:
• the pixel-sampling locations that are associated with each of a plurality of two-dimensional spatial slices of the three-dimensional mask in the spatial domain;
• and
• the pixel-sampling locations that are associated with each of a plurality of one-dimensional temporal slices of the three-dimensional mask in the temporal domain;
• generate a sample of the video by sampling the sequence of frames using the three-dimensional mask;
• and
• generate a reconstructed video from the generated sample of the video using a machine-learning model.

A system comprising:

• one or more processors;
• and
• one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
• receive a video comprising a sequence of frames;
• access a three-dimensional mask that specifies pixel-sampling locations, the three-dimensional mask having (1) a first dimension and a second dimension corresponding to a spatial domain and (2) a third dimension corresponding to a temporal domain, wherein a blue noise property is present in:
• the pixel-sampling locations that are associated with each of a plurality of two-dimensional spatial slices of the three-dimensional mask in the spatial domain;
• and
• the pixel-sampling locations that are associated with each of a plurality of one-dimensional temporal slices of the three-dimensional mask in the temporal domain;
• generate a sample of the video by sampling the sequence of frames using the three-dimensional mask;
• and
• generate a reconstructed video from the generated sample of the video using a machine-learning model.