Miao

reproduction problem

1

Thanks for sharing your works. i use a quick evaluation as your code on fold 2. the meanIoU is only 48.7% (51.3% in article) and multi-scale cannot improve the preformance...

about the search indices

1

` for x in range(1, max_radius): search_dirs.append((0, x)) for y in range(1, max_radius): for x in range(-max_radius + 1, max_radius): if x * x + y * y < max_radius...

Question about meanIoU binary

3

Thanks for sharing your work! I am a little confused about the metrics. It is said in the code that the mean IoU binary regards all class as one foreground...

when there are only RGB images, how to predict the depth? After reading the paper, i still didn't understand it.