Today I’ve learned about bilinear interpolation for images, so I’d like to share it here.
To simplify the concept, here is an example if we were to upscale an image by a factor of 2 using bilinear interpolation.
For semantic segmentation models, it is said that upscaling using bilinear interpolation by a factor of up to 8 has quite good performance for the image restoration phase.(Research: Deeplab).
