System and method for synthesizing data for training statistical models in different imaging modalities including polarized images

• Main Authors: KALRA ANUPREET, KRISHNAKUMAR VENKATARAMAN, CADAMBI, ALESSANDRO
• Format: Patent
• Language: Chinese; English
• Published: 02.12.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

A method of generating a composite image of a virtual scene includes: placing a three-dimensional (3-D) model in a 3-D virtual scene by a composite data generator implemented by a processor and a memory; adding, by the synthetic data generator, illumination to the 3-D virtual scene, the illumination comprising one or more illumination sources; applying, by a synthesis data generator, imaging modality-specific materials to the 3-D model of an object in the 3-D virtual scene according to a selected multi-modality imaging modality, each of the imaging modality-specific materials comprising an empirical model; and rendering, by the composite data generator, a two-dimensional image of the 3-D virtual scene based on the selected multi-modal imaging modality to generate a composite image according to the selected multi-modal imaging modality. 一种生成虚拟场景的合成图像的方法，包括：通过由处理器和存储器实施的合成数据生成器在3-D虚拟场景中放置三维(3-D)模型；通过所述合成数据生成器向所述3-D虚拟场景添加照明，所述照明包括一个或多个照明源；通过合成数据生成器根据选定的多模态成像模态将成像模态特定的材料应用到所述3-D虚拟场景中的物体的所述3-D模型，所述成像模态特定的材料中的每个包括经