Method and device for shooting image, medium, electronic equipment and method for training model

Abstract

Embodiments of the application disclose a method and a device for shooting an image, a storage medium, electronic equipment and a method for training a model, wherein the electronic equipment is capable of receiving an input shooting command; then shooting a to-be-shot scene according to the shooting command to obtain a shot image; and performing de-noising processing on the shot image through animage de-noising model, and using a de-noised image obtained through the de-noising processing as a result image of the shooting command, wherein the image de-noising model is obtained by model training in which multiple image sets shot in advance are used as training inputs, and de-noised images which are obtained by synthetic de-noising respectively performed on the multiple image sets are usedas target outputs. Through adoption of the above technical scheme, as long as the training of the image de-noising model is completed, when subsequent shooting is performed, the image de-noising modelobtained by training can be used to perform de-noising processing on shot images, thereby saving the time of shooting multiple images and performing image synthesis, and achieving the purpose of improving an image de-noising efficiency.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image capturing method, device, storage medium, electronic equipment and model training method. Background technique [0002] At present, users usually use electronic devices with a shooting function (such as mobile phones, tablet computers, etc.) to take images to record what happens around them, the scenery they see, etc. anytime and anywhere. However, due to hardware limitations of the electronic device itself, when shooting night scenes or low-brightness scenes, the captured images often have more noise. In related technologies, image noise reduction is performed by means of composite noise reduction, but this method of noise reduction needs to take multiple images at the same time, and then synthesize the multiple images obtained into one image. The whole process takes a long time, resulting in Image noise reduction is less efficient. Contents of the...

AI Technical Summary

Problems solved by technology

However, due to the hardware limitations of the electronic device itself, when shooting night scenes or low-brightness scenes, the captured images often have more noise

In related technologies, image noise reduction is performed by means of composite noise reduction, but this noise reduction method needs to shoot multiple images at the same time, and then synthesize the multiple images obtained into one image. The whole process takes a long time, resulting in Image noise reduction is less efficient

Images