quan-meng / gnerf

[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )
MIT License
227 stars 27 forks source link

problem on image size #3

Open artist-duan opened 2 years ago

artist-duan commented 2 years ago

Dear Authors, Thanks for the amazing work.

I have some problem when the size of image h not equal to w, when cal psnr on phase B the render image is [w,h], but the real img is [h,w], this problem also show on tensorboard 'rgb' detail: similarity.py mse value = (image_pred - image_gt) ** 2

Thanks for your help.

quan-meng commented 2 years ago

Are you using the most recently pushed code? The bug is fiexed in the commit "Fixed bug in dtu dataset (the order of image width and hight)" on Nov 11, 2021.

artist-duan commented 2 years ago

I used the latest code, but it does not converge when training phase B