Scalable Large Scene Neural View Synthesis

Re:Scalable Large Scene Neural View Synthesis by ToJans on Saturday February 12, 2022 @01:35AM (#30310490)

Imagine matching the output of the block nerf + GPS data combined with a live camera view to get ultra-high positioning precision... Or to use changes over time in 2 views to detect anomalies or maintenance heuristics... So many potentially interesting use cases

[ Parent | on HN ]

Re:Scalable Large Scene Neural View Synthesis by WithinReason on Saturday February 12, 2022 @06:06AM (#30311838)

Actually, determining camera position is done quite differently and more efficiently: https://en.wikipedia.org/wiki/Simultaneous_localization_and_...

(I spent about a year writing an optimiser for camera localisation from multiple views)

[ Parent | on HN ]

Re:Scalable Large Scene Neural View Synthesis by var_cw on Saturday February 12, 2022 @04:23AM (#30311323)

I wish a day comes when the compute at inference is more optimized than the raw camera sensor processing

Is this too much to ask for? :/

[ Parent | on HN ]