search

creiser / kilonerf

Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
471 stars 52 forks source link

Inconsistent LPIPS implementation? #8

Closed sunset1995 closed 2 years ago

sunset1995 commented 2 years ago

Really great work!

I have a question about current LPIPS implementation. From the lpips document, the input RGB images should be in scale [-1,+1]. But it seems that the current implementation feed RGB in [0, 1] to lpips.

I have also traced the baseline NSVF's lpips evaluation and they scale the RGB from [0, 1] to [-1, 1] (see their code).

I would appreciate clarification about this. Thanks!

creiser commented 2 years ago

Thanks for pointing this out. I will fix that and change the numbers if there is any deviation from the different range. I suspect if there is any deviation it will be very small.