公开(公告)号：US20230360170A1

公开(公告)日：2023-11-09

申请号：US18055716

申请日：2022-11-15

Applicant: Adobe Inc.

Inventor： Mohammad Reza KARIMI DASTJERDI ,  Yannick Hold-Geoffroy ,  Vladimir KIM ,  Jonathan EISENMANN ,  Jean-François LALONDE

IPC: G06T3/40 ,  G06T7/00 ,  G06V10/776 ,  G06T3/00 ,  G06V10/774

CPC classification number: G06T3/4023 ,  G06T3/0012 ,  G06T3/0093 ,  G06T3/4046 ,  G06T7/0002 ,  G06V10/774 ,  G06V10/776 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30168

Abstract: Embodiments are disclosed for generating 360-degree panoramas from input narrow field of view images. A method of generating 360-degree panoramas may include obtaining an input image and guide, generating a panoramic projection of the input image, and generating, by a panorama generator, a 360-degree panorama based on the panoramic projection and the guide, wherein the panorama generator is a guided co-modulation generator network trained to generate a 360-degree panorama from the input image based on the guide.

公开(公告)号：US20220229943A1

公开(公告)日：2022-07-21

申请号：US17153380

申请日：2021-01-20

Applicant: ADOBE INC.

Inventor： Mikaela Angelina UY ,  Vladimir KIM ,  Minhyuk SUNG ,  Noam AIGERMAN ,  Siddhartha CHAUDHURI

IPC: G06F30/10 ,  G06N3/08 ,  G06T19/20

Abstract: Embodiments provide systems, methods, and computer storage media for generating a 3D model from a target 2D image or 3D point cloud (e.g., generated by a 3D scan). Given a particular target, a retrieval network retrieves or identifies a source model from a database, and a deformation network deforms the source model to fit the target. In some cases, joint learning is employed to enable the retrieval and deformation networks to jointly learn a deformation-aware retrieval embedding space and an individualized deformation space for each source model. In some cases, the retrieval network retrieves based on distance in the deformation-aware retrieval embedding space, enabling the retrieval module to retrieve a source model that best fits to the target after deformation. In some cases, a deformation is decomposed into a plurality of per-part deformations, and/or and the retrieval embedding space is used to select training data.