| CPC G06T 15/20 (2013.01) [G06T 7/90 (2017.01); G06T 2207/10024 (2013.01)] | 20 Claims |

|
1. A method for semantic-driven intelligent reconstruction of a large-scene sparse light field, comprising:
acquiring a semantic primitive set of a multi-view image set, wherein the semantic primitive set comprises at least one semantic primitive, and the multi-view image set comprises at least one image;
acquiring a coordinate offset by inputting coordinate information and a feature vector corresponding to a first grid sampling point of the semantic primitive set into a first network model, and acquiring a second grid of the semantic primitive set based on the coordinate offset and geometric attribute information of the semantic primitive set;
acquiring first feature information of a second grid sampling point by inputting coordinate information and a feature vector corresponding to the second grid sampling point, and an observation angle value into a second network model, and acquiring second feature information of the semantic primitive set based on the first feature information, wherein the first feature information comprises a visibility value and a color value of the second grid sampling point; and
acquiring a light field reconstruction result of the multi-view image set based on an observation angle value of the semantic primitive set and third feature information extracted from the second feature information, wherein the third feature information comprises a spatial offset, a visibility value and a color value of the semantic primitive set.
|