Virtual viewpoint quality evaluation method based on visual masking effect

Abstract

The invention discloses a virtual viewpoint quality evaluation method based on a visual masking effect. According to the method, the types of virtual viewpoint rendering distortions are fully considered, offset compensation is performed on a virtual viewpoint image, the offset compensation process aims at special distortions such as a pixel point offset in the rendering of a virtual viewpoint, the affect of the pixel point position offset on the quality of the virtual viewpoint image is well eliminated, and thus subjective and objective quality results of the virtual viewpoint image are more accordant; the human visual characteristics are fully considered, a visual sensitive mask pattern of a reference image is extracted, the affect of distortion of a visual insensitive area in the virtual viewpoint image on the objective quality evaluation result is eliminated, and thus the objective quality evaluation result is more accordant with human visual characteristics; a distortion amplitude masking effect and a distortion distribution masking effect are fully considered, the distortion masking pattern of the virtual viewpoint image is computed for extracting areas with large distortion amplitudes and concentrated distortion distributions, and the affects of the distortions with different amplitudes and different distributions on the human visual subjective quality are effectively distinguished.

Description

technical field [0001] The invention relates to a technology for evaluating the performance of a virtual viewpoint and a rendering system, in particular to a method for evaluating the quality of a virtual viewpoint based on a visual masking effect. Background technique [0002] In recent years, stereoscopic video technology has developed rapidly. The Free Viewpoint Video system (FVV, FreeViewpointVideo) is a further development on the basis of 3D video, which can enable users to obtain better visual experience. The depth-based virtual viewpoint rendering (DIBR, DepthImageBasedRendering) technology is the core of the FVV system, which can overcome the limitation of the camera's ability to obtain real viewpoints and generate enough virtual viewpoints. However, there are many types of distortions in the virtual viewpoint generated by rendering, which will seriously affect the 3D visual experience. Therefore, it is necessary to propose an evaluation scale to measure the quality...

AI Technical Summary

Problems solved by technology

If there are multiple distortions in the virtual viewpoint, the distortion with large amplitude and concentrated distribution will cover up the distortion with small amplitude and discrete distribution, which will affect the visual effect of human eyes

[0010] From the above content, it can be seen that many new types of distortion will be introduced in the process of virtual viewpoint rendering, and the influence of human visual characteristics and distortion distribution will be added at the same time. The traditional pixel-based quality evaluation method cannot effectively evaluate the quality of virtual viewpoint.

Images