Image processing apparatus and method

Abstract

The invention relates to an image processing apparatus and method. The image processing apparatus includes a converter that converts an input image into a depth image to obtain a converted depth for each pixel of the input image; and a classifier that classifies between the converted depth and a real depth from a depth data set, where the classifier and the converter are trained until the classifier cannot distinguish the converted depth from the real depth. By using the image processing apparatus and method according to the present disclosure, depth can be learned from a single image by confrontation training, which not only can learn the depth of the single image by a converter, but also can understand the high order consistency of the depth by a classifier. Through such adversarial training, the converter may output a depth map having a similar distribution as a real depth map.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, in particular to single image depth estimation based on adversarial learning. Background technique [0002] This section provides background information related to the present disclosure which is not necessarily prior art. [0003] With the rapid development of modern cameras, it is now possible to acquire a large number of images with high resolution. Restoring the three-dimensional (3D) structure of a scene or object from these images is of great significance for many computer applications such as entertainment, augmented reality, monument protection, robotics, and so on. Depth estimation from multiple viewpoints is a key step in image-based 3D modeling and has been extensively studied by researchers. [0004] In the prior art, methods for estimating depth from a single image mainly utilize some monocular depth cues, such as focus, occlusion, etc. However, these methods are...

AI Technical Summary

Problems solved by technology

However, these methods usually ignore the relationship between adjacent depths on the depth map, which is very important for generating high-quality depth maps.

Although some graphical model-based methods can enhance the local smoothness of the depth map to a certain extent, it is difficult to model the high-order consistency of the depth

Images