While technically very impressive you would hope this effort would be reflected in a higher quality of resulting movie, but that doesn't seem to be the case.

It's interesting that even their details mention essentially using it as a ML training set data generator for later:

"By analysing training sets that demonstrate how a 3D character should look as it moves, Ziva RealTime learns to reconstruct the shape of that character at realtime speeds.

Character effects that traditionally require seconds or even minutes per frame are reproduced in milliseconds. This unlocks the potential to deploy full-fidelity character assets into Virtual Production, Virtual Reality, or game environments and directly interact with them."