Closed ewrfcas closed 3 years ago
The bicubic downsampling in MATLAB is different from the one in opencv. The one in MATLAB contains some anti-aliasing operations. Therefore, when you use the pre-trained GLEAN on the images downgraded by opencv, it is normal that you get a poor result.
The result from area
is better in this case but it is still far from optimal.
Thanks I have tried matlab resize, and it works much better now
Hi, thanks for your kind response! I have another question about the resize method used in python. Since you have mentioned that the matlab default bicubic resize should be used in GLEAN. However, I think maybe the resize method is LINEAR_AREA? Here is the resized result in python opencv (cv2) bicubic:
area:
Then, the output result of bicubic is
And the result of area is
It can be seen that area is much better than bicubic. But the area result still has some artifacts (hair). I think maybe the resize method still has some problems? The sample is named 1009.jpg in Celeba-HQ.