公开(公告)号：US20240303789A1

公开(公告)日：2024-09-12

申请号：US18389072

申请日：2023-11-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ashkan MIRZAEI ,  Tristan TY AUMENTADO-ARMSTRONG ,  Konstantinos G. DERPANIS ,  Igor GILITSCHENSKI ,  Aleksai LEVINSHTEIN ,  Marcus BRUBAKER

IPC: G06T5/00 ,  G06T15/20

CPC classification number: G06T5/77 ,  G06T15/20

Abstract: Provided is a method of training a neural radiance field and producing a rendering of a 3D scene from a novel viewpoint with view-dependent effects. The neural radiance field is initially trained using a first loss associated with a plurality of unmasked regions associated with a reference image and a plurality of target images. The training may also be updated using a second loss associated with a depth estimate of a masked region in the reference image. The training may also be further updated using a third loss associated with a view-substituted image associated with a respective target image. The view-substituted image is a volume rendering from the reference viewpoint across pixels with view-substituted target colors. In some embodiments, the neural radiance field is additionally trained with a fourth loss. The fourth loss is associated with dis-occluded pixels in a target image.