Machine-learning models trained to modify image illumination without ground-truth images

One or more non-transitory computer readable storage media embodying instructions and coupled to one or more processors that are operable to execute the instructions to train a machine-learning model for modifying a facial illumination in an image, comprising:

• access an initial image comprising a human face having an initial illumination;
• determine one or more illumination priors for the initial image;
• provide the initial image and the one or more illumination priors to the machine-learning model;
• receive, from the machine-learning model, a set of correction operators identifying a modified illumination for the human face;
• create, based at least on the set of correction operators and the initial image, a modified image having the modified illumination;
• create, based on the modified image, a reconstructed initial image comprising the human face having a reconstructed illumination;
• and
• adjust one or more parameters of the machine-learning model by minimizing a loss function based on a difference between the initial image with the initial illumination and the reconstructed initial image with the reconstructed illumination.

A method comprising:

• accessing an input image comprising a hominid face having a starting illumination;
• determining, by a machine-learning model trained to modify facial illumination without using ground-truth training data, an illumination modification to the starting illumination, wherein the machine-learning model trained to modify facial illumination without using ground-truth training data comprises a plurality of model parameters, the model parameters have been determined at least in part during training by:
• receiving (1) an initial image comprising a human face having an initial illumination and (2) one or more illumination priors;
• providing a set of correction operators comprising a modified illumination for the human face;
• creating, based at least on the set of correction operators and the initial image, a modified image having the modified illumination;
• creating, based on the modified image, a reconstructed initial image comprising the human face having a reconstructed illumination;
• and
• adjusting one or more of the plurality of model parameters by minimizing a loss function based on a difference between the initial image with the initial illumination and the reconstructed initial image of the human face with the reconstructed illumination, wherein the reconstructed initial image is based at least on the set of correction operators;
• and
• creating an output image comprising the hominid face illuminated as modified by the illumination modification.

One or more non-transitory computer readable storage media embodying instructions and coupled to one or more processors that are operable to execute the instructions to:

• access an input image comprising a hominid face having a starting illumination;
• determine, by a machine-learning model trained to modify facial illumination without using ground-truth training data, an illumination modification to the starting illumination, wherein the machine-learning model trained to modify facial illumination without using ground-truth training data comprises a plurality of model parameters, the model parameters have been determined at least in part during training by:
• receiving (1) an initial image comprising a human face having an initial illumination and (2) one or more illumination priors;
• providing a set of correction operators comprising a modified illumination for the human face;
• creating, based at least on the set of correction operators and the initial image, a modified image having the modified illumination;
• creating, based on the modified image, a reconstructed initial image comprising the human face having a reconstructed illumination;
• and
• adjusting one or more of the plurality of model parameters by minimizing a loss function based on a difference between the initial image with the initial illumination and the reconstructed initial image of the human face with the reconstructed illumination, wherein the reconstructed initial image is based at least on the set of correction operators;
• and
• create an output image comprising the hominid face illuminated as modified by the illumination modification.