fit_a_nef.metrics.simse

fit_a_nef.metrics.simse(a: Array, b: Array) → Array

Vectorized version of simse. Takes similar arguments as simse but with additional array axes over which simse is mapped.

Original documentation:

Returns the Scale-Invariant Mean Squared Error between a and b.

For each image pair, a scaling factor for b is computed as the solution to the following problem:

min_alpha || vec(a) - alpha * vec(b) ||_2^2

where a and b are flattened, i.e., vec(x) = np.flatten(x). The MSE between the optimally scaled b and a is returned: mse(a, alpha*b).

This is a scale-invariant metric, so for example: simse(x, y) == sims(x, y*5).

This metric was used in “Shape, Illumination, and Reflectance from Shading” by Barron and Malik, TPAMI, ‘15.

param a:

First image (or set of images).

type a:

jax.Array

param b:

Second image (or set of images).

type b:

jax.Array

return:

SIMSE between a and b.

rtype:

jax.Array