Facial image deformation method, apparatus, electronic device and computer readable medium

Patent metadata

Field	Value
Publication number	US-12475525-B2
Application number	US-202017776300-A
Country	US
Kind code	B2
Filing date	Nov 6, 2020
Priority date	Nov 13, 2019
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

Embodiments of the present disclosure provide a facial image deformation method and apparatuses, an electronic device, and a computer-readable media. A specific embodiment of the method comprises: determining an anchor point corresponding to a dragging operation in response to detecting the dragging operation on a target facial image, wherein the anchor point corresponds to a part displayed in the target facial image; determining an offset of the anchor point based on a movement amount corresponding to the dragging operation; and deforming the target facial image based on the offset of the anchor point.

First claim

What is claimed is:

1 . A facial image deformation method, comprising:
determining an anchor point corresponding to a dragging operation in response to detecting the dragging operation on a target facial image, wherein the anchor point corresponds to a part displayed in the target facial image; determining an offset of the anchor point based on a movement amount corresponding to the dragging operation; deforming the target facial image based on the offset of the anchor point, wherein the deforming the target facial image based on the offset of the anchor point comprises: deforming the target facial image based on the offset of the anchor point in response to determining that the offset of the anchor point meets a preset condition; and before deforming the target facial image based on the offset of the anchor point in response to determining that the offset of the anchor point meets a preset condition, determining an offset of a longitudinally adjacent anchor point of the anchor point in response to determining that a longitudinal offset of the anchor point is greater than or equal to a longitudinal distance between the anchor point and the longitudinally adjacent anchor point; wherein the deforming the target facial image based on the offset of the anchor point comprises: deforming the target facial image based on the offset of the anchor point and the offset of the longitudinally adjacent anchor point, wherein the longitudinal offset of the anchor point is a longitudinal component of the offset of the anchor point, and a longitudinal distance between the anchor point and the longitudinally adjacent anchor point is a longitudinal component of a distance between the anchor point and the longitudinally adjacent anchor point.

2 . The facial image deformation method according to claim 1 , wherein the anchor point corresponding to the part displayed in the target facial image is obtained through the following steps:
performing key point detection on the target facial image to obtain a set of key points; and determining the anchor point corresponding to the part displayed in the target facial image based on the set of key points.

3 . The facial image deformation method according to claim 2 , wherein the determining the anchor point corresponding to the part displayed in the target facial image based on the set of key points comprises:
calculating a weighted sum of coordinates of multiple key points in the set of key points corresponding to the part, so as to determine coordinates of the anchor point corresponding to the part displayed in the target facial image.

4 . The facial image deformation method according to claim 1 , wherein the determining an offset of the anchor point based on a movement amount corresponding to the dragging operation comprises:
determining an offset of the anchor point based on a movement amount corresponding to the dragging operation and pose information of a face displayed in the target facial image, wherein the pose information is used to represent rotation angle of the face.

5 . An electronic device, comprising:
one or more processors; and a memory device having stored thereon one or more programs, which when executed by the one or more processors cause the one or more processors to implement the facial image deformation method according to claim 1 .

6 . A non-transitory computer program product, comprising a computer program, which when executed implements the facial image deformation method according to claim 1 .

7 . A facial image deformation apparatus, comprising:
a first determining unit configured to determine an anchor point corresponding to a dragging operation in response to detecting the dragging operation on a target facial image, wherein the anchor point corresponds to a part displayed in the target facial image; a second determining unit configured to determine an offset of the anchor point based on a movement amount corresponding to the dragging operation; a deformation processing unit configured to deform the target facial image based on the offset of the anchor point, wherein the deformation processing unit is configured to deform the target facial image based on the offset of the anchor point in response to determining that the offset of the anchor point meets a preset condition; and a third determining unit configured to, before the deformation processing unit deforms the target facial image based on the offset of the anchor point in response to determining that the offset of the anchor point meets a preset condition, determine an offset of a longitudinally adjacent anchor point of the anchor point in response to determining that a longitudinal offset of the anchor point is greater than or equal to a longitudinal distance between the anchor point and the longitudinally adjacent anchor point, wherein the deformation processing unit is configured to deform the target facial image based on the offset of the anchor point and the offset of the longitudinally adjacent anchor point, wherein the longitudinal offset of the anchor point is a longitudinal component of the offset of the anchor point, and a longitudinal distance between the anchor point and the longitudinally adjacent anchor point is a longitudinal component of a distance between the anchor point and the longitudinally adjacent anchor point.

8 . A non-transitory computer-readable storage medium having stored thereon instructions which, when executed by a processor, cause the processor to:
determining an anchor point corresponding to a dragging operation in response to detecting the dragging operation on a target facial image, wherein the anchor point corresponds to a part displayed in the target facial image; determining an offset of the anchor point based on a movement amount corresponding to the dragging operation; deforming the target facial image based on the offset of the anchor point, wherein the deforming the target facial image based on the offset of the anchor point comprises: deforming the target facial image based on the offset of the anchor point in response to determining that the offset of the anchor point meets a preset condition; and before deforming the target facial image based on the offset of the anchor point in response to determining that the offset of the anchor point meets a preset condition, determining an offset of a longitudinally adjacent anchor point of the anchor point in response to determining that a longitudinal offset of the anchor point is greater than or equal to a longitudinal distance between the anchor point and the longitudinally adjacent anchor point, wherein the deforming the target facial image based on the offset of the anchor point comprises: deforming the target facial image based on the offset of the anchor point and the offset of the longitudinally adjacent anchor point, wherein the longitudinal offset of the anchor point is a longitudinal component of the offset of the anchor point, and a longitudinal distance between the anchor point and the longitudinally adjacent anchor point is a longitudinal component of a distance between the anchor point and the longitudinally adjacent anchor point.

9 . The non-transitory computer-readable storage medium according to claim 8 , wherein the non-transitory computer-readable storage medium further stores program instructions which, when executed by the processor, cause the processor to:
performing key point detection on the target facial image to obtain a set of key points; and determining the anchor point corresponding to the part displayed in the target facial image based on the set of key points.

10 . The non-transitory computer-readable storage medium according to claim 8 , wherein

Assignees

• Beijing Bytedance Network Tech Co Ltd

Inventors

• ZhuGe Jingjing
• Ni Guangyao
• Zhang Shupeng
• Xue Xiaole

Classifications

• G06F3/04845 Primary

  for image manipulation, e.g. dragging, rotation, expansion or change of colour · CPC title

• G06V40/165

  using facial parts and geometric relationships · CPC title

• G06F3/04883

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G06T3/18 Primary

  Image warping, e.g. rearranging pixels individually · CPC title