cutcutcodec.core.analysis.video.quality.vmaf¶

cutcutcodec.core.analysis.video.quality.vmaf(dis: Tensor, ref: Tensor, *, _model=None, **kwargs) → Tensor[source]¶

Compute the Video Multi-Method Assessment Fusion of 2 images.

Parameters¶

dis, refarraylike: The 2 images to be compared, of shape ([*batch], height, width, channels=3). The frames are assumed to be in YUV (y’pbpr) in range [0, 1]. Gamut and EOTF must be standard rgb.
threadsint, optional: Defines the number of threads. The value -1 means that the function uses as many calculation threads as there are cores. The default value (0) allows the same behavior as (-1) if the function is called in the main thread, otherwise (1) to avoid nested threads. Any other positive value corresponds to the number of threads used.

Returns¶

vmafarraylike: The learned perceptual image patch similarity of each image.

Notes¶

This static function does not require the installation of vmaf.

Examples¶

>>> import numpy as np
>>> from cutcutcodec.core.analysis.video.quality import vmaf
>>> np.random.seed(0)
>>> ref = np.random.random((720, 1080, 3))  # It could also be a torch array list...
>>> ref[..., 1:3] -= 0.5  # because pbpr in [-0.5, 0.5]
>>> dis = 0.8 * ref + 0.2 * np.random.randn((720, 1080, 3))
>>> vmaf(dis, ref).round(1)
>>>