Multiresolution implicit representations

A network can represent an image by mapping a position to a colour. Below, Sine–ReLU, SIREN and multiresolution hash grids each fit the same image using less than 1 MiB. The enlarged eye makes the effect of the representation easy to see.

Cat video reconstruction

Original video alongside ReLU and multiresolution hash-grid reconstructions. Both fitted models use less than 1 MiB.

Bach reconstruction

A single network reconstructs this Bach recording by mapping time to amplitude. The fitted hash-grid model uses less than half a MiB.

Images, audio and video share the model design, with weights fitted separately for each signal.