公开(公告)号：US20240070884A1

公开(公告)日：2024-02-29

申请号：US17896574

申请日：2022-08-26

Applicant: ADOBE INC.

Inventor： Taesung PARK ,  Sylvain PARIS ,  Richard ZHANG ,  Elya SHECHTMAN

IPC: G06T7/40 ,  G06T5/50

CPC classification number: G06T7/40 ,  G06T5/50 ,  G06T2207/10028

Abstract: An image processing system uses a depth-conditioned autoencoder to generate a modified image from an input image such that the modified image maintains an overall structure from the input image while modifying textural features. An encoder of the depth-conditioned autoencoder extracts a structure latent code from an input image and depth information for the input image. A generator of the depth-conditioned autoencoder generates a modified image using the structure latent code and a texture latent code. The modified image generated by the depth-conditioned autoencoder includes the structural features from the input image while incorporating textural features of the texture latent code. In some aspects, the autoencoder is depth-conditioned during training by augmenting training images with depth information. The autoencoder is trained to preserve the depth information when generating images.