Mojo function
cubic_kernel
cubic_kernel(x: SIMD[float32, 1]) -> SIMD[float32, 1]
Cubic interpolation kernel matching PyTorch/torchvision's BICUBIC filter.
This uses the Catmull-Rom variant (Robidoux cubic) with a = -0.75, which is what PyTorch uses in get_cubic_upsample_coefficients. (Source). This also matches OpenCV's interpolateCubic.
Args:
- x (
SIMD[float32, 1]): Distance from the center point.
Returns:
Weight contribution based on the distance.
cubic_kernel(x: SIMD[dtype, size]) -> SIMD[dtype, size]
Cubic interpolation kernel matching PyTorch/torchvision's BICUBIC filter.
This uses the Catmull-Rom variant (Robidoux cubic) with a = -0.75, which is what PyTorch uses in get_cubic_upsample_coefficients. (Source). This also matches OpenCV's interpolateCubic.
Args:
- x (
SIMD[dtype, size]): Distance from the center point.
Returns:
Weight contribution based on the distance.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!