Image processing method and device, terminal equipment and readable storage medium

Abstract

The invention provides an image processing method and device, terminal equipment and a readable storage medium. The method comprises the steps: determining a real view angle within a preset range from a target view angle, wherein the target view angle is a view angle where a real image cannot be collected, and the real view angle is a view angle where the real image can be collected; obtaining a real image collected from the real view angle; obtaining depth projection images of the real image for the target visual angle under a plurality of different depth values; and obtaining a virtual view angle image of the target view angle according to the plurality of obtained depth projection images, and taking the virtual view angle image as an image collected from the target view angle. According to the method, the virtual view angle image of the virtual view angle can be accurately synthesized under the condition that the depth of the real image cannot be accurately estimated, so that the synthesized virtual view angle image is closer to the real image at the virtual view angle, the fluency of video shooting is ensured, and the watching experience of a user is enhanced.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to an image processing method, device, terminal equipment and readable storage medium. Background technique [0002] In a video shooting scene, in order to enable the audience to obtain an immersive viewing experience, multiple camera equipments are usually arranged around the shooting point to shoot videos from multiple directions. However, this layout method requires more camera equipment, which increases the workload of camera equipment installation, calibration, debugging, and data transmission synchronization. In the related art, a free viewing angle synthesis algorithm is used to synthesize a virtual viewing angle image of a viewing angle without the camera equipment installed by using the real image collected by the camera equipment, thereby reducing the deployment quantity of the camera equipment. [0003] However, when synthesizing virtual perspective image...

AI Technical Summary

Problems solved by technology

However, the accuracy of some current depth estimation algorithms is not high, and more accurate depth information cannot be obtained. Therefore, a large error will be introduced when the virtual perspective image is actually synthesized, resulting in the final synthetic virtual perspective image and the actual image at the virtual perspective. The gap is too large and the image quality is low

Images