Multi-source light field fusion rendering method and device and storage medium

• Main Authors: ZHANG LONG, HAO DONGLI, XING SHUJUN, SANG XINZHU, YU XUNBO
• Format: Patent
• Language: Chinese; English
• Published: 01.03.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The embodiment of the invention provides a multi-source light field fusion rendering method and device and a storage medium, and the method comprises the steps: obtaining the depth information of a target object in a multi-view image based on the EPI domain conversion of a polar plane image; removing a non-target object in the multi-view image based on the depth information of the target object to obtain a target object image; determining multi-source scene data of the target object based on the target object image; and fusing the multi-source scene data to render the target object image to obtain a rendering result. According to the multi-source light field fusion rendering method and device and the storage medium provided by the embodiment of the invention, depth extraction can be carried out on the multi-view image through EPI domain conversion, then non-target objects are removed according to depth information, fusion rendering of a multi-source scene is carried out, and a scene reconstruction rendering i