Granted Patent B2

US 12,425,529 · App. 18/253,186 · Granted Sep 23, 2025

Inventors: Qinghua Zhou (Beijing, CN); Shiyin Wang (Beijing, CN)

Assignee: Beijing Bytedance Network Technology Co., Ltd.

H04N5/2621G06T5/50G06T5/70G06T7/12G06V10/25H04N5/272G06T2207/20221

Abstract

Claims (56)

1. A video processing method, comprising:

fixing a target frame image in a target video in response to a triggering instruction; and

removing a target object in the target frame image, and performing a padding operation on a target area in the target frame image so as to generate and display a padding frame image, wherein the target area comprises a vacant area after the target object is removed from the target frame image,

wherein the removing the target object in the target frame image and performing the padding operation on the target area in the target frame image comprises:

identifying various pixel points in the target frame image by using a preset object segmentation model so as to generate a target binary image with the same size as the target frame image; and

determining the target area of the target object in the target frame image according to the target binary image, wherein the target area in the target binary image comprises various pixel points with pixel values being target values.

2. The video processing method according to claim 1 , wherein after the generating and displaying the padding frame image, the method further comprises:

playing a first special effect sequence frame by using the padding frame image as a background, wherein the first special effect sequence frame is used to dynamically display special effect particles according to a preset path.

3. The video processing method according to claim 1 , wherein after the fixing the target frame image of the target video, the method further comprises:

displaying a preset second special effect, wherein the preset second special effect is used to enable the target frame image to present a visual blurring effect.

4. The video processing method according to claim 1 , wherein after the fixing the target frame image of the target video, the method further comprises:

displaying a preset third special effect, wherein the preset third special effect is used to enable the target frame image to present a visual shaking effect.

5. The video processing method according to claim 1 , wherein after generating and displaying the padding frame image, the method further comprises:

continuously performing a padding operation on the target area in a subsequent frame image of the target video, wherein the subsequent frame image is located after the padding frame image in the target video.

6. The video processing method according to claim 1 , further comprising:

determining that the target object is an object of a target type, wherein the target object or the object of the target type comprises at least one of a target person, a target animal, or a target building.

7. The video processing method according to claim 1 , wherein the triggering instruction comprises at least one of a target gesture instruction, a target voice instruction, a target expression instruction, a target limb instruction, or a target text instruction.

8. The video processing method according to claim 1 , wherein the performing the padding operation on the target area in the target frame image comprises:

fusing the target binary image with the target frame image to obtain a model inputting image;

inputting the model inputting image into an image patching model to generate a processing frame image; and

replacing the target area in the target frame image with a target area in the processing frame image to generate the padding frame image.

9. The video processing method according to claim 8 , wherein the image patching model is provided in a terminal device, and the terminal device processes the target video based on the image patching model.

10. The video processing method according to claim 8 , wherein the inputting the model inputting image into the image patching model to generate the processing frame image comprises:

inputting the model inputting image into a first image patching model to generate a first padding image;

performing pixel truncation on the first padding image by using a preset pixel threshold value so as to generate a second padding image;

inputting the second padding image into a second image patching model to generate a third padding image, wherein the second image patching model has higher patching precision than the first image patching model; and

performing pixel truncation on the third padding image by using the preset pixel threshold value so as to generate a fourth padding image, wherein the processing frame image comprises the fourth padding image.

11. An electronic device, comprising:

a processor; and

a memory, configured to store a computer program;

a display, configured to display a video after processing by the processor;

wherein the processor is configured to:

fix a target frame image in a target video in response to a triggering instruction;

remove a target object in the target frame image, and performing a padding operation on a target area in the target frame image so as to generate and display a padding frame image, wherein the target area comprises a vacant area after the target object is removed from the target frame image;

identify various pixel points in the target frame image by using a preset object segmentation model so as to generate a target binary image with the same size as the target frame image; and

determine the target area of the target object in the target frame image according to the target binary image, wherein the target area in the target binary image comprises various pixel points with pixel values being target values.

12. The electronic device according to claim 11 , wherein the processor is further configured to:

play a first special effect sequence frame by using the padding frame image as a background, wherein the first special effect sequence frame is used to dynamically display special effect particles according to a preset path.

13. The electronic device according to claim 11 , wherein the processor is further configured to:

display a preset second special effect, wherein the preset second special effect is used to enable the target frame image to present a visual blurring effect.

14. The electronic device according to claim 11 , wherein the processor is further configured to:

display a preset third special effect, wherein the preset third special effect is used to enable the target frame image to present a visual shaking effect.

15. The electronic device according to claim 11 , wherein the processor is further configured to:

continuously perform a padding operation on the target area in a subsequent frame image of the target video, wherein the subsequent frame image is located after the padding frame image in the target video.

16. A non-transitory computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the following operations are executed:

fixing a target frame image in a target video in response to a triggering instruction; and

removing a target object in the target frame image, and performing a padding operation on a target area in the target frame image so as to generate and display a padding frame image, wherein the target area comprises a vacant area after the target object is removed from the target frame image,

wherein the removing the target object in the target frame image and performing the padding operation on the target area in the target frame image comprises:

identifying various pixel points in the target frame image by using a preset object segmentation model so as to generate a target binary image with the same size as the target frame image; and

determining the target area of the target object in the target frame image according to the target binary image, wherein the target area in the target binary image comprises various pixel points with pixel values being target values.

17. The non-transitory computer readable storage medium according to claim 16 , wherein after the generating and displaying the padding frame image, the following operation are further executed:

playing a first special effect sequence frame by using the padding frame image as a background, wherein the first special effect sequence frame is used to dynamically display special effect particles according to a preset path.

18. The non-transitory computer readable storage medium according to claim 16 , wherein after the fixing the target frame image of the target video, the following operation are further executed:

displaying a preset second special effect, wherein the preset second special effect is used to enable the target frame image to present a visual blurring effect.

19. The non-transitory computer readable storage medium according to claim 16 , wherein after the fixing the target frame image of the target video, the following operation are further executed:

displaying a preset third special effect, wherein the preset third special effect is used to enable the target frame image to present a visual shaking effect.

Assignments (3)

Priority Claims (1)

Continuity (1)

References Cited (54)