IMAGE AUGMENTATION AND NEURAL NETWORK TRAINING METHOD AND APPARATUS, DEVICE AND STORAGE MEDIUM

摘要

Disclosed in embodiments of the present application are an image augmentation and neural network training method and apparatus, a device, and a storage medium, the method comprising: acquiring a three-dimensional image carrying a target object marked with set key points, wherein the three-dimensional image is obtained by reconstructing two-dimensional images of the target object; acquiring a defective two-dimensional image corresponding to a projection after the three-dimensional image is rotated by a set angle, the defective two-dimensional image comprising converted coordinates of the set key points of the target object corresponding to the set angle; performing feature extraction on the defective two-dimensional image on the basis of a trained neural network, and repairing the defective two-dimensional image on the basis of a correspondence between the converted coordinates of the set key points and the attitude so as to obtain a repaired image corresponding to the defective two-dimensional image; and obtaining an augmented image set of the target object on the basis of the repaired image.