search

YoYo000 / MVSNet

MVSNet (ECCV2018) & R-MVSNet (CVPR2019)
MIT License
1.39k stars 303 forks source link

Why inverse depth divided by 1 ? #150

Closed AsDeadAsADodo closed 1 year ago

AsDeadAsADodo commented 1 year ago

In R-MVSNET training loss section , we apply the inverse depth to sample the depth values in order to efficiently handle reconstructions with wide depth ranges. In homography_warping.py line 66-69

        inv_depth_start = tf.reshape(tf.div(1.0, depth_start), [])
        inv_depth_end = tf.reshape(tf.div(1.0, depth_end), [])
        inv_depth = tf.lin_space(inv_depth_start, inv_depth_end, depth_num)
        depth = tf.div(1.0, inv_depth)

Correct me if I'm wrong , basically did something like this 1672593490878 Why ? is this a way to draw the network's attention to focus on the nearest planes? Any help would be great !

AsDeadAsADodo commented 1 year ago

@kwea123 @YoYo000 I'm sorry to bother you , but could you please help me with this?