Abstract: This application disclose a feature extraction method performed by a computer device. The method includes: shooting a cone-shaped group of viewing-frustum rays from a target character object for a hit object in a three-dimensional scene picture; determining object attribute information of the hit object based on an interaction between the viewing-frustum rays and the hit object; performing vector conversion on the object attribute information of the hit object, to obtain a ray-feature vector; collecting, by using a location of the target character object as a collection center, a plurality of height-value matrices corresponding to different granularities; performing feature dimension reduction on the height-value matrix corresponding to each granularity, to obtain a height-map feature vector; and integrating the ray-feature vector and the height-map feature vector into a three-dimensional scene feature.

Abstract: A depth information calculation method and device based on a light-field-binocular system. The method includes obtaining a far-distance disparity map based on binocular information of calibrated input images, setting respective first confidences pixels in the disparity map, and obtaining a first target confidence; detecting the first confidence of a pixel being smaller than a preset value and responsively determining a new disparity value based on light field information of the input images, determining an update depth value based on the new disparity value, and obtaining a second target confidence of the pixel; and combining the far-distance disparity map and a disparity map formed by the new disparity value on a same unit into an index map, combining the first confidence and the first target confidence into a confidence map, optimizing the index and confidence maps to obtain a final disparity map, which is converted to a final depth map.

Abstract: A depth information calculation method and device based on a light-field-binocular system. The method includes obtaining a far-distance disparity map based on binocular information of calibrated input images, setting respective first confidences pixels in the disparity map, and obtaining a first target confidence; detecting the first confidence of a pixel being smaller than a preset value and responsively determining a new disparity value based on light field information of the input images, determining an update depth value based on the new disparity value, and obtaining a second target confidence of the pixel; and combining the far-distance disparity map and a disparity map formed by the new disparity value on a same unit into an index map, combining the first confidence and the first target confidence into a confidence map, optimizing the index and confidence maps to obtain a final disparity map, which is converted to a final depth map.