公开(公告)号：US12141929B1

公开(公告)日：2024-11-12

申请号：US18082213

申请日：2022-12-15

Applicant: Amazon Technologies, Inc.

Inventor： Shan Yang ,  Xi Zhang ,  Kenan Deng ,  Junbang Liang ,  Tomas F. Yago Vicente ,  Ramesh Krishnamurthy ,  Esra Gokcen Boduroglu ,  Yu Lou

IPC: G06T19/00 ,  G06T19/20

Abstract: Devices and techniques are described for augmented reality furniture layout recommendation. In some examples, first data comprising a three dimensional (3D) model of a room is received. Second data representing an intended usage of the room may be received. A first machine learning model may generate a first collection template using the first data and the second data. The first collection template may include first bounding box data representing a first category of furniture and second bounding box data representing a second category of furniture. The first bounding box data representing a first bounding box having a first size and located at a first position within the 3D model at a first orientation. The second bounding box data representing a second bounding box having a second size and located at a second position within the 3D model at a second orientation.

公开(公告)号：US11869163B1

公开(公告)日：2024-01-09

申请号：US17478655

申请日：2021-09-17

Applicant: Amazon Technologies, Inc.

Inventor： Junbang Liang ,  Ming Lin ,  Javier Romero Gonzalez-Nicolas ,  Adam Douglas Peck ,  Chetan Shivarudrappa

IPC: G06T19/20 ,  G06N3/088 ,  G06F30/27 ,  G06F113/12 ,  G06V10/40 ,  G06F18/214 ,  G06N3/045

CPC classification number: G06T19/20 ,  G06F18/214 ,  G06F30/27 ,  G06N3/045 ,  G06N3/088 ,  G06V10/40 ,  G06F2113/12 ,  G06T2200/24 ,  G06T2219/2004 ,  G06T2219/2021

Abstract: Systems and methods are provided for machine learning-based rendering of a clothed human with a realistic 3D appearance by virtually draping one or more garments or items of clothing on a 3D human body model. The machine learning model may be trained to drape a garment on a 3D body mesh using training data that includes a variety 3D body meshes reflecting a variety of different body types. The machine learning model may include an encoder trained to extract body features from an input 3D mesh, and a decoder network trained to drape the garment on the input 3D mesh based at least in part on spectral decomposition of a mesh associated with the garment. The trained machine learning model may then be used to drape the garment or a variation of the garment on a new input body mesh.

公开(公告)号：US20230306699A1

公开(公告)日：2023-09-28

申请号：US17701556

申请日：2022-03-22

Applicant: Amazon Technologies, Inc.

Inventor： Junbang Liang ,  Sunil Sharadchandra Hadap ,  Vidya Narayanan

IPC: G06T19/20 ,  G06T17/20

CPC classification number: G06T19/20 ,  G06T17/20 ,  G06T2210/21 ,  G06T2210/16 ,  G06T2219/2004

Abstract: Systems and methods are provided for improved 3D garment draping simulation. A garment pattern may be obtained that includes a number of flat, 2D garment panels designated to be connected at seam lines. Triangulated versions of each of the 2D garment panels may then be positioned in 3D virtual space relative to a 3D model of a human body, such that one or more annotated points on each triangulated garment panel are aligned with a corresponding labelled point or region on the 3D body. A warped 3D garment mesh may then be generated by repeatedly applying geometric manipulations to the triangulated garment panels to connect their corresponding seam lines without causing collisions between the triangulated garment panels and the 3D body. This warped 3D garment may then be provided as input to a physics-based draping simulator.