公开(公告)号：US20180260975A1

公开(公告)日：2018-09-13

申请号：US15457192

申请日：2017-03-13

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： KALYAN K. SUNKAVALLI ,  XIAOHUI SHEN ,  MEHMET ERSIN YUMER ,  MARC-ANDRÉ GARDNER ,  EMILIANO GAMBARETTO

IPC: G06T7/90

CPC classification number: G06T7/00 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/08 ,  G06N20/10 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods and systems are provided for using a single image of an indoor scene to estimate illumination of an environment that includes the portion captured in the image. A neural network system may be trained to estimate illumination by generating recovery light masks indicating a probability of each pixel within the larger environment being a light source. Additionally, low-frequency RGB images may be generated that indicating low-frequency information for the environment. The neural network system may be trained using training input images that are extracted from known panoramic images. Once trained, the neural network system infers plausible illumination information from a single image to realistically illumination images and objects being manipulated in graphics applications, such as with image compositing, modeling, and reconstruction.