Resolution of images in training

apchenstu / mvsnerf

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

MIT License

675 stars 84 forks source link

Resolution of images in training #50

Open hengfei-wang opened 2 years ago

hengfei-wang commented 2 years ago

Hi,

I saw your code resizes the input images to 3:2. Can I use images with different resolution ratio to train the model? Do I need to revise some code?

Thanks

apchenstu commented 2 years ago

Hi, yeah you definitely can use another resolution but must be 32*n since there are downsampling operations in the feature extraction