Xiao Pan
Hi, May I ask how did you get the coordinate of the sampled point in the tri-plane space? In the original NeRF, the sampled points are under the world coordinate....
Thanks for your reply. Could you please provide more details about the scaling process? In my understanding, scaling the unlimited world coordinate to [-1, 1] needs to know the upper...
Thank you for your help~ I will read the referenced code Best,
The chamfer distance defined[ here ](http://graphics.stanford.edu/courses/cs468-17-spring/LectureSlides/L14%20-%203d%20deep%20learning%20on%20point%20cloud%20representation%20(analysis).pdf)is not normalized and is squared. I think it depends on which kind of formulation you used.
Same here. I am in need of DTU ckpts for comparisons.
> @TreB1eN, actually, I used your pretrained model SE-IR-50 and evaluation script from insightface and loose crop data from VGG group to evaluate the performance on IJBB, the results turn...
Same here.
Hi @ajabri @AndyTang15 , May I ask where did you download the VIP dataset? The official link in the original paper is expired. Is there any cloud drive version?
> Hi Allan, > > Happy new year! And many thanks for releasing the code of this great work! > > I used the codebase and the pretrained model provided...
I also encountered this issue when using fp16. In my experiments, after I reduce the EPS from 1e-20 to 1e-7, the NAN in loss will disappear, but the performance is...