Image processing method and device and storage medium

Abstract

Embodiments of the invention disclose an image processing method and device, and a storage medium. The method comprises the steps of obtaining a depth image edge corresponding to a depth image and a color image edge corresponding to a color image, wherein the color image and the depth image are image information of the same shooting scene; determining a filtering window corresponding to each pixelpoint in the depth image edge from the depth image by utilizing the color image and the color image edge to obtain a plurality of filtering windows; and for each pixel point in the depth image edge,carrying out box type filtering processing by utilizing the corresponding filtering window in the plurality of filtering windows.

Description

technical field [0001] The embodiments of the present application relate to the technical field of image processing, and in particular, to an image processing method and device, and a storage medium. Background technique [0002] Depth images can reflect the depth information that is missing when a real 3D scene is projected on a 2D imaging plane, and play an important role in applications such as 3D reconstruction and blurring. [0003] Currently, depth image acquisition technologies mainly include two types: active acquisition and passive calculation. Among them, the active acquisition mainly uses the depth camera to directly acquire the spatial depth information of the 3D scene, and the passive calculation mainly uses the stereo matching of multi-view images to calculate the parallax, and obtains the depth information according to the multi-view geometric relationship. [0004] Using the above two techniques for depth image acquisition, the obtained depth image usually h...

AI Technical Summary

Problems solved by technology

[0004] Using the above two techniques for depth image acquisition, the obtained depth image usually has problems such as noise and errors. Therefore, it is necessary to optimize the depth image using algorithms such as joint bilateral filtering, guided filtering, and weighted median filtering.

However, using common filtering methods for depth image processing can easily lead to blurred edges in the depth image and poor depth image quality

Images