Jingnan Gao
Jingnan Gao
@flyingshan I think it somehow mismatches the "T" for the original value which lies in [near, far] but the value of world_tx could be very large sometimes, is it because...
Yeah, I've tried this way, but the "T" caculated seems not correspond to all the points by this way, I think it's because the uniqueness of the sampleing method since...
Good to know !
Thanks for the reply! Okay, setting the loss to be 0 works definitely and thanks for the clarification.