US 2022/0101578 A1 · GENERATING COMPOSITE IMAGES WITH OBJECTS FROM DIFFERENT TIMES

Abstract

Methods, systems, and non-transitory computer readable media are disclosed for generating a composite image comprising objects in positions from two or more different digital images. In one or more embodiments, the disclosed system receives a sequence of images and identifies objects within the sequence of images. In one example, the disclosed system determines a target position for a first object based on detecting user selection of the first object in the target position from a first image. The disclosed system can generate a fixed object image comprising the first object in the target position. The disclosed system can generate preview images comprising the fixed object image with the second object sequencing through a plurality of positions as seen in the sequence of images. Based on a second user selection of a desired preview image, the disclosed system can generate the composite image.

Claims20

Dependent claims

A non-transitory computer readable medium for generating images, the non-transitory computer readable medium comprising instructions that, when execute by at least one processor, cause a computing device to:

segment instances of a first object and a second object in a sequence of images;
receive, via a graphical user interface at a user client device, a selection of the first object in a first position from a first image;
based on the selection, generate a fixed object image comprising the first object fixed in the first position;
present, via the graphical user interface, the fixed object image with the first object fixed in the first position and segmented instances of the second object sequencing through a plurality of positions from images of the sequence of images;
receive, via the graphical user interface, a selection of the second object in a second position from a second image;
and
based on the selection of the second object, generate a composite image comprising the first object in the first position and the second object in the second position.

4 more elements

A system comprising:

at least one non-transitory computer readable storage medium storing a sequence of images and
at least one computing device configured to cause the system to:
segment instances of a first object and a second object utilizing a neural network by generating object masks for instances of the first object and the second object in the images of the sequences of images;
receive, via a graphical user interface at a user client device, a selection of the first object in a first position from a first image;
based on the selection, generate a fixed object image comprising the first object fixed in the first position by removing an object mask comprising the second object from the first image;
present, via the graphical user interface, the fixed object image with the first object fixed in the first position and the second object sequencing through a plurality of positions by superimposing object masks of the second object in the plurality of positions from the sequence of images;
receive, via the graphical user interface, a selection of the second object in a second position from a second image of the sequence of images;
and
based on the selection of the second object, generate a composite image comprising the first object in the first position and the second object in the second position by inserting the object mask corresponding to the second object in the second position into the fixed object image.

6 more elements

Dependencies are inferred from the claim text.

Generating composite images with objects from different times

Life of this patent

Generating composite images with objects from different times

Life of this patent

Abstract

Claims20