Method, apparatus, electronic device, storage medium and system for vision task execution

A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program is configured to be executed by a processor to:

• acquire raw image data which is collected by an image sensor and not processed by an image signal processor (ISP);
• and
• input the raw image data into a trained first raw image neural network for executing a target vision task to obtain a vision task processing result output by the first raw image neural network,
• wherein the first raw image neural network is obtained based on training with a raw image training set,
• the computer program being further configured to:
• input traditional training images with labels into an aliasing model trained in advance to obtain sub-Nyquist image data, wherein the raw image training set further comprises the sub-Nyquist image data.

An electronic device, comprising:

• a memory, having a computer program stored thereon;
• and
• a processor, used for executing the computer program in the memory to implement steps of a method, the method comprising:
• acquiring raw image data which is collected by an image sensor and not processed by an image signal processor (ISP);
• and
• inputting the raw image data into a trained first raw image neural network for executing a target vision task to obtain a vision task processing result output by the first raw image neural network,
• wherein the first raw image neural network is obtained based on training with a raw image training set,
• training of the first raw image neural network further comprises:
• inputting traditional training images with labels into an aliasing model trained in advance to obtain sub-Nyquist image data, wherein the raw image training set further comprises the sub-Nyquist image data.