Image processing method and device

Patent metadata

Field	Value
Publication number	US-11455773-B2
Application number	US-201917044181-A
Country	US
Kind code	B2
Filing date	May 6, 2019
Priority date	May 31, 2018
Publication date	Sep 27, 2022
Grant date	Sep 27, 2022

Abstract

Embodiments of the present disclosure provide a method and apparatus for processing an image. An embodiment of the method includes: acquiring a two-dimensional garment image, where the two-dimensional garment image includes a style identifier of a garment; selecting a three-dimensional garment model matching the style identifier from a pre-established set of three-dimensional garment models, wherein the three-dimensional garment model includes scatter points labeled thereon; labeling the two-dimensional garment image with scatter points based on a pre-established coordinate mapping relationship between the two-dimensional garment image and the three-dimensional garment model and the scatter points of the selected three-dimensional garment model; generating a three-dimensional garment image of the acquired two-dimensional garment image based on the selected three-dimensional garment model and a result of the labeling.

First claim

What is claimed is:

1. A method for processing an image, comprising:
acquiring a two-dimensional garment image, wherein the two-dimensional garment image includes a style identifier of a garment;
selecting a three-dimensional garment model matching the style identifier from a pre-established set of three-dimensional garment models, wherein the three-dimensional garment model includes scatter points labeled thereon;
labeling the two-dimensional garment image with scatter points based on a pre-established coordinate mapping relationship between the two-dimensional garment image and the three-dimensional garment model and the scatter points of the selected three-dimensional garment model;
performing coordinate transformation on the scatter points of the acquired two-dimensional garment image, and determining coordinate information of the scatter points after the coordinate transformation;
generating a primitive having a preset shape based on the coordinate information of the scatter points after the coordinate transformation, the primitive comprising a preset number of scatter points after the coordinate transformation and a connection relationship between the scatter points;
rasterizing the primitive to obtain a fragment set of the primitive, wherein a fragment in the fragment set includes a color value and texture coordinate information;
performing texture coordinate mapping on the fragment set to obtain pixels of the selected three-dimensional garment model; and
generating the three-dimensional garment image based on the obtained pixels.

2. The method according to claim 1 , wherein
the connection relationship comprises a number of other scatter points connected to each scatter point, and relative coordinate information between the other scatter points connected to each scatter point and the each scatter point.

3. The method according to claim 2 , wherein the fragment in the fragment set further comprise texture material information; and
the generating the three-dimensional garment image based on the obtained pixels comprises:
determining illumination information of the obtained pixels based on the texture material information and the preset light source coordinate information;
processing the obtained pixels based on light source color information and the determined illumination information;
generating the three-dimensional garment image based on the processed pixels.

4. The method according to claim 2 , wherein after the generating the three-dimensional garment image based on the obtained pixels, the method further comprises:
smoothing texture of the three-dimensional garment image.

5. The method according to claim 1 , wherein the set of three-dimensional garment models is established by:
acquiring a set of two-dimensional sample garment images, the set of two-dimensional sample garment images including two-dimensional sample garment image sequences of at least one style, for a two-dimensional sample garment image sequence of each style in the two-dimensional sample garment image sequences of at least one style, performing: extracting feature points of the two-dimensional sample garment image sequence; constructing a fundamental matrix based on the extracted feature points; establishing a three-dimensional garment model based on the constructed fundamental matrix and calibration parameters of a pre-calibrated camera, wherein the camera is a camera acquiring the two-dimensional sample garment image sequence;
generating the set of three-dimensional garment models based on the established at least one three-dimensional garment model.

6. The method according to claim 1 , wherein after the generating the three-dimensional garment image of the acquired two-dimensional garment image, the method further comprises:
receiving somatotype information;
selecting a virtual three-dimensional model matching the somatotype information from a preset virtual three-dimensional model set;
setting, based on a preset coordinate mapping relationship between the virtual three-dimensional model and the three-dimensional garment model, the three-dimensional garment image onto the selected virtual three-dimensional model and presenting.

7. An apparatus for processing an image, the apparatus comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, causing the at least one processor to perform operations, the operations comprising:
acquiring a two-dimensional garment image, wherein the two-dimensional garment image includes a style identifier of a garment;
selecting a three-dimensional garment model matching the style identifier from a pre-established set of three-dimensional garment models, wherein the three-dimensional garment model includes scatter points labeled thereon;
labeling the two-dimensional garment image with scatter points based on a pre-established coordinate mapping relationship between the two-dimensional garment image and the three-dimensional garment model and the scatter points of the selected three-dimensional garment model;
performing coordinate transformation on the scatter points of the acquired two-dimensional garment image, and determining coordinate information of the scatter points after the coordinate transformation;
generating a primitive having a preset shape based on the coordinate information of the scatter points after the coordinate transformation, the primitive comprising a preset number of scatter points after the coordinate transformation and a connection relationship between the scatter points;
rasterizing the primitive to obtain a fragment set of the primitive, wherein a fragment in the fragment set includes a color value and texture coordinate information; and
performing texture coordinate mapping on the fragment set to obtain pixels of the selected three-dimensional garment model;
generating the three-dimensional garment image based on the obtained pixels.

8. The apparatus according to claim 7 , wherein
the connection relationship comprises a number of other scatter points connected to each scatter point, and relative coordinate information between the other scatter points connected to each scatter point and the each scatter point.

9. The apparatus according to claim 8 , wherein the fragment in the fragment set further comprise texture material information; and
the generating the three-dimensional garment image based on the obtained pixels is further configured to:
determining illumination information of the obtained pixels based on the texture material information and the preset light source coordinate information;
processing the obtained pixels based on light source color information and the determined illumination information;
generating the three-dimensional garment image based on the processed pixels.

10. The apparatus according to claim 8 , wherein the operations further comprise:
smoothing texture of the three-dimensional garment image.

11. The apparatus according to claim 7 , wherein the set of three-dimensional garment models is established by:
acquiring a set of two-dimensional sample garment images, the set of two-dimensional sample garment images including two-dimensional sample garment image sequences of at least one style, for a two-dimensional sample garment image sequence of each style in the two-dimensional sample garment image sequences of at least one style, performing: extracting feature points of the two-dimensional sample garment image sequence; constructing a fundamental matrix based on the extracted feature points; establishing a three-dimensional garment model based on the constructed fundamental matrix and calibration parameters of a pre-

Assignees

• Beijing Jingdong Shangke Information Technology Co Ltd
• Beijing Jingdong Century Trading Co Ltd

Inventors

• He Jinping

Classifications

• G06T17/10 Primary

  Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes · CPC title

• G06T2219/2021

  Shape modification · CPC title

• G06T7/80

  Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration · CPC title

• G06T19/20 Primary

  Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts · CPC title

• G06T7/529

  from texture · CPC title