Model training method and device, frame image generation method and device, frame insertion method and device, equipment and medium

Abstract

The invention provides a model training method and device, a frame image generation method and device, a frame insertion method and device, equipment and a medium and relates to the technical field ofmodel training. The method is applied to a neural network model and adopts a first feature extraction module to extract local features of front and back frame images of a sample; a second feature extraction module is adopted to extract non-local features of front and back frame images of the sample; a frame synthesis module is adopted to generate a sample intermediate frame image according to thesynthesis features of the local features and the non-local features; and the neural network model is trained according to the sample intermediate frame image and the corresponding label intermediateframe image to obtain a trained neural network model. According to the neural network model obtained by training based on the mode, the receptive field is expanded, the learning ability of large changes in front and back frame images is enhanced, and when the front and back frame images are processed based on the trained neural network model, the generated middle frame image is more accurate.

Description

technical field [0001] The present invention relates to the technical field of model training, in particular, to a method, device, equipment and medium for model training, frame image generation, and frame insertion. Background technique [0002] The frame rate refers to the frequency at which continuous images are displayed on the monitor. The higher the frame rate within a certain range, the smoother the picture. Due to force majeure such as cost issues, hardware limitations, and network transmission, usually only low frame rate pictures can be obtained. Therefore, intermediate frames can be generated between existing frames by frame interpolation to make the picture smoother. [0003] In the related art, a convolution kernel is trained for each pixel in the previous frame image and the rear frame image by means of kernel estimation, and the intermediate frame image is generated by performing convolution operations with several independent convolution kernels on the front ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a model training, frame image generation, frame interpolation method, device, equipment, and medium to solve the above-mentioned deficiencies in the prior art, so as to solve the kernel estimation method adopted in the related art, based on convolution Check the local information of the image for processing. When the current frame image and the subsequent frame image change greatly, it is easy to cause the problem that the generated intermediate frame image is inaccurate.

Images