Vision-based quality metric for three dimensional video

摘要

In general, techniques are described for determining a vision-based quality metric for three-dimensional (3D) video. A device (12, 14) comprising a 3D analysis unit (24, 48) may implement these techniques to compute a 3D objective metric (36, 60). The 3D analysis unit (24, 48) estimates an ideal depth map (62, 70) that would generate a distortion limited image view using DIBR-based 3D video data (34) and then derives one or more distortion metrics (64, 72) based on quantitative comparison of the ideal depth map (62, 70) and a depth map (28, 58) used in the generation of the DIBR-based 3D video data (34). Based on the derived one or more distortion metrics (64, 72), the 3D analysis unit (24, 48) computes the objective metric (36, 60) to quantify visual quality of DIBR-based video data (34). The 3D objective metric (36, 60) may be used to alter or otherwise adjust depth estimation and encoding/decoding parameters to correct for expected visual discomfort.

主权项

1. A method for obtaining an objective metric to quantify the visual quality of depth-image-based rendering (DIBR)-based three-dimensional (3D) video data, the method comprising:
estimating an ideal depth map that would generate a distortion limited image view using DIBR-based 3D video data based on a combination of a view generated from the DIBR-based 3D video data, a focal length of a virtual 3D image capture device, and a baseline of the virtual 3D capture device; deriving distortion metrics comprising a spatial error outliers distortion metric that is based on a difference between an ideal depth map and the depth map of the DIBR-based 3D video data, a temporal error outliers distortion metric that is based on a difference between the ideal depth map and the depth map of the DIBR-based 3D video data for at least two consecutive frames of the 3D video, and a temporal inconsistency distortion metric that is based on a difference between depth maps used to generate DIBR-based 3D video data and a successive DIBR-based 3D video data; and computing the objective metric to quantify visual quality of the DIBR-based 3D video data based on the derived distortion metrics comprising the spatial error outliers distortion metric, the temporal error outliers distortion metric, and the temporal inconsistency distortion metric.