Image pickup apparatus for inferring noise and learning device

An image pickup apparatus comprising:

• a solid-state image pickup device including known pixels that emit pixel signals having noise superimposed thereon;
• at least one processor or circuit configured to function as:
• a communication unit configured to acquire a learned model from a learning device that is configured to:
• (i) input, to a model-to-be-learned, image data (i.a) that is acquired from the solid-state image pickup device and (i.b) that has not been corrected based on first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon,
• (ii) detect an error in an output of the model-to-be-learned by using the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon as supervised data for correcting the output of the model-to-be learned, and
• (iii) update the model-to-be-learned based on the error in the output of the model-to-be learned detected using the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon to thereby generate the learned model;
• and
• an inference unit configured to infer a pixel signal, emitted from a pixel of the solid-state image pickup device different from the known pixels, on which noise is superimposed by inputting image data, to the learned model, corrected based on the first correction information.

An image pickup apparatus comprising:

• a solid-state image pickup device including known pixels that emit pixel signals having noise superimposed thereon;
• and
• at least one processor or circuit configured to function as:
• a communication unit configured to acquire an inference result from an inference device that is configured to infer a pixel signal, emitted from a pixel of the solid-state image pickup device different from the known pixels, on which noise is superimposed by inputting an image data, to a learned model, corrected based on first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon, the learned model having been generated by a learning device configured to:
• (i) input, to a model-to-be-learned, image data (i.a) that is acquired from the solid-state image pickup device and (i.b) that has not been corrected based on the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon,
• (ii) detect an error in an output of the model-to-be-learned by using the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon as supervised data for correcting the output of the model-to-be learned, and
• (iii) update the model-to-be-learned based on the error in the output of the model-to-be learned detected using the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon to thereby generate the learned model.

A learning device comprising:

• at least one processor or circuit configured to function as a learning unit configured to:
• (i) input, to a model-to-be-learned, image data (i.a) that is acquired from a solid-state image pickup device including known pixels that emit pixel signals having noise superimposed thereon and (i.b) that has not been corrected based on first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon,
• (ii) detect an error in an output of the model-to-be-learned by using the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon as supervised data for correcting the output of the model-to-be learned,
• (iii) update the model-to-be-learned based on the error in the output of the model-to-be learned detected using the first correction information identifying the pixel signals, emitted from the known pixels, having the noise superimposed thereon to thereby generate a learned model.