-
Notifications
You must be signed in to change notification settings - Fork 15
Detail about the smooth upsample #7
Comments
Not exactly. Smooth upsampling is achieved by applying tent-shaped convolution kernels consecutively (in our case, in 3 steps), which effectively changes the shape of the interpolation kernel to be smoother, and significantly reduces upsampling artifacts. For example, for a downsampling factor s = 64, instead of upsampling with a single tent kernel with a support of 64 × 64, we use tent kernels with a support of 4 × 4 three times, one after the other. We chose this method of linear upsampling rather than a more advanced method owing to its separability and efficient implementation. The confidence is at low resolution and is applied at low resolution. The guided filter is solved at low resolution, and then upsampled. |
Thank you for the quick reply. However, we can’t realize the effect compared with the paper. |
I would like to follow up on this question:
|
Apologies: I missed the message from @Ianresearch . We upsample with a bilinear (tent) kernel sequentially (3 times). I hope this is clearer now. |
I am also struggling to reproduce the results. I have similar problems as @Ianresearch described in 2. @orlyliba Could you please provide me with some answers to my questions?
|
I think they are the same. Our implementation is with Halide, not CV, so we implemented upsampling ourselves.
(answer to both 2 and 3) You can just ignore the kernel interpretation if you'd like, and think of this as concatenated bilinear upsampling.
The procedure is consecutive bilinear upsampling. Instead of bilinear upsampling by a scale of x64, we upsample x4 three times and get to the same final resolution. I hope this is clearer now. |
Hi! Please see this code submission for the guided filter: 8a35938 |
Hello, we realize the modified guided filter follow the pseudocode. The smooth upsampling we do as follow:
Is it the right processing procedure to do the smooth upsampling?
If the processing procedure is right, how to choose the kernel for smooth filter?
Another question is that how to use the weighted downsample when inference. Because of the confidence map is low resolution , how to use the function(4):modified_guided_filter, which the C is high resolution.
Thank you.
The text was updated successfully, but these errors were encountered: