公开(公告)号：US20220343522A1

公开(公告)日：2022-10-27

申请号：US17233122

申请日：2021-04-16

Applicant: ADOBE INC.

Inventor： Sai Bi ,  Zexiang Xu ,  Kalyan Krishna Sunkavalli ,  David Jay Kriegman ,  Ravi Ramamoorthi

IPC: G06T7/514 ,  G06T17/20 ,  H04N13/111 ,  H04N13/128 ,  H04N13/282

Abstract: Enhanced methods and systems for generating both a geometry model and an optical-reflectance model (an object reconstruction model) for a physical object, based on a sparse set of images of the object under a sparse set of viewpoints. The geometry model is a mesh model that includes a set of vertices representing the object's surface. The reflectance model is SVBRDF that is parameterized via multiple channels (e.g., diffuse albedo, surface-roughness, specular albedo, and surface-normals). For each vertex of the geometry model, the reflectance model includes a value for each of the multiple channels. The object reconstruction model is employed to render graphical representations of a virtualized object (a VO based on the physical object) within a computation-based (e.g., a virtual or immersive) environment. Via the reconstruction model, the VO may be rendered from arbitrary viewpoints and under arbitrary lighting conditions.

公开(公告)号：US20220335636A1

公开(公告)日：2022-10-20

申请号：US17231833

申请日：2021-04-15

Applicant: ADOBE INC.

Inventor： Sai Bi ,  Zexiang Xu ,  Kalyan Krishna Sunkavalli ,  Milos Hasan ,  Yannick Hold-Geoffroy ,  David Jay Kriegman ,  Ravi Ramamoorthi

IPC: G06T7/586 ,  G06T9/00 ,  G06T15/50 ,  G06T15/06

Abstract: A scene reconstruction system renders images of a scene with high-quality geometry and appearance and supports view synthesis, relighting, and scene editing. Given a set of input images of a scene, the scene reconstruction system trains a network to learn a volume representation of the scene that includes separate geometry and reflectance parameters. Using the volume representation, the scene reconstruction system can render images of the scene under arbitrary viewing (view synthesis) and lighting (relighting) locations. Additionally, the scene reconstruction system can render images that change the reflectance of objects in the scene (scene editing).

公开(公告)号：US12211225B2

公开(公告)日：2025-01-28

申请号：US17231833

申请日：2021-04-15

Applicant: ADOBE INC.

Inventor： Sai Bi ,  Zexiang Xu ,  Kalyan Krishna Sunkavalli ,  Miloš Hašan ,  Yannick Hold-Geoffroy ,  David Jay Kriegman ,  Ravi Ramamoorthi

IPC: G06T7/586 ,  G06T9/00 ,  G06T15/06 ,  G06T15/50

Abstract: A scene reconstruction system renders images of a scene with high-quality geometry and appearance and supports view synthesis, relighting, and scene editing. Given a set of input images of a scene, the scene reconstruction system trains a network to learn a volume representation of the scene that includes separate geometry and reflectance parameters. Using the volume representation, the scene reconstruction system can render images of the scene under arbitrary viewing (view synthesis) and lighting (relighting) locations. Additionally, the scene reconstruction system can render images that change the reflectance of objects in the scene (scene editing).

公开(公告)号：US11669986B2

公开(公告)日：2023-06-06

申请号：US17233122

申请日：2021-04-16

Applicant: ADOBE INC.

Inventor： Sai Bi ,  Zexiang Xu ,  Kalyan Krishna Sunkavalli ,  David Jay Kriegman ,  Ravi Ramamoorthi

IPC: G06T7/514 ,  G06T17/20 ,  H04N13/111 ,  H04N13/282 ,  H04N13/128

CPC classification number: G06T7/514 ,  G06T17/20 ,  H04N13/111 ,  H04N13/128 ,  H04N13/282 ,  G06T2207/10012 ,  G06T2207/10028

Abstract: Enhanced methods and systems for generating both a geometry model and an optical-reflectance model (an object reconstruction model) for a physical object, based on a sparse set of images of the object under a sparse set of viewpoints. The geometry model is a mesh model that includes a set of vertices representing the object's surface. The reflectance model is SVBRDF that is parameterized via multiple channels (e.g., diffuse albedo, surface-roughness, specular albedo, and surface-normals). For each vertex of the geometry model, the reflectance model includes a value for each of the multiple channels. The object reconstruction model is employed to render graphical representations of a virtualized object (a VO based on the physical object) within a computation-based (e.g., a virtual or immersive) environment. Via the reconstruction model, the VO may be rendered from arbitrary viewpoints and under arbitrary lighting conditions.