Disparity Refinement

[youmi-zym]

Disparity Refinement

[haofeixu]

Thanks for your interest.
Unfortunately, we didn't have such a comparison. However, we anticipate the performance will be not that good, as the resolution of estimated disparity without refinement is relatively low and the residual learning (i.e., refinement) scheme has been proved to be effective in many previous works (e.g., StereoNet). You can train with our code to see what happens.
Sorry about that we have no plan to extend the deformable conv to 3D currently.

[youmi-zym]

Thanks

[XYZ-qiyh]

Hello, @haofeixu
As I know, the scale_factor is the ratio of left_img Height and low_disp Height.
But, why the disp need to multiply the scale_factor?

aanet/nets/refinement.py

Lines 45 to 47 in 5e2359c

	scale_factor = left_img.size(-1) / low_disp.size(-1)
	disp = F.interpolate(low_disp, size=left_img.size()[-2:], mode='bilinear')
	disp = disp * scale_factor # scale correspondingly

[haofeixu]

Hi @Todd-Qi ,

As the low resolution disparity is upsampled to higher resolution, it's magnitude needs to be scaled correspondingly.
That is, a 1-pixel disparity at 1/4 resolution corresponds to 2-pixel for 1/2 resolution.

[XYZ-qiyh]

Thanks for your clear explanation.