search

haofeixu / aanet

[CVPR'20] AANet: Adaptive Aggregation Network for Efficient Stereo Matching
Apache License 2.0
521 stars 100 forks source link

why do we can't multiply scale in file model.py when interpoate the pred_disp? #45

Closed dreamhua82 closed 3 years ago

dreamhua82 commented 3 years ago

Hi, I have two questions to ask you. 1、In your model.py # line 97, why don't multiply the resize scale as do in refinement module? Is that mean, we have finished training, This is the last result, so we don't multiply the scale any more when we do interpolate? 2、why don't use the full resolution to construct multi-scale cost volume. (i.e. H, H/2, H/3), is that only for save GPU memory? Thanks,

haofeixu commented 3 years ago

  1. the scale factor is acutally multiplied: https://github.com/haofeixu/aanet/blob/f689abf81ef072b4e50eb480d3a73db66eebda44/model.py#L97-L98

  2. Of course you can use full resolution, but it will cost too much memory.