# US 2025/0094106 A1 · Image display method, image display apparatus, device and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0094106 A1
- Document ID: US20250094106A1
- Status: Published application
- Kind: A1
- Application number: 18/727,250
- Filed: 2022-06-14
- Published: 2025-03-20
- Earliest claimed: 2022-04-22
- Assignees: Southern University of Science and Technology
- Applicants: Southern University of Science and Technology
- Inventors: Xiaowei SUN; Philip Anthony SURMAN; Chaojian ZHANG; Zhenwei YAO
- Web page: https://patentgrep.com/patent/US20250094106A1

## CPC

- G06F 3/14: Digital output to display device {; Cooperation and interconnection of the display device with other functional units}
- G06T 7/50: Depth or shape recovery
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An image display method, an image display apparatus, a device and a storage medium. The method includes, acquiring an original image (S100); performing image analysis on the original image according to a preset image analysis model, so as to obtain a target depth map (S200); performing image synthesis on the target depth map according to a preset virtual viewpoint synthesis algorithm, so as to obtain a plurality of target images of different viewing angles (S300), compiling the plurality of target images of different viewing angles, so as to obtain a target image set (S400); and transmitting the target images in the target image set to different directions by means of a light-splitting device, so as to present the plurality of target images of different viewing angles (S500)

## Claims

### Claim 1

An image display method, comprising:
acquiring an original image;
performing image analysis on the original image according to a pre-set image analysis model to obtain a target depth map;
performing image synthesis on the target depth map according to a pre-set virtual viewpoint synthesis algorithm to obtain a plurality of target images from different viewing angles, wherein each of the plurality of target images has a respective one of multiple viewing angles;
collecting the plurality of the target images to obtain a target image set; and
emitting, by a light splitting element, each of the plurality of the target images in the target image set to a respective one of multiple directions to display the plurality of the target images from different viewing angles, such that a target user in a first position with a first primary vision area and a corresponding first viewing angle information views a first set of the plurality of the target images.

### Claim 2 (depends on 1)

The image display method according to claim 1, wherein both a current primary vision area and current viewing angle information of the target user change with a position where the target user is located, after emitting, by the light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of the target images from different viewing angles, the method further comprises:
adjusting a target image displayed in the current a primary vision area of the target user, comprising:
in response to the target user moving to a second position from the first position acquiring second viewing angle information of the target user as the current viewing angle information;
determining a second primary vision area corresponding to the second viewing angle information as the current primary vision area of the target user according to the second viewing angle information; and
switching the first set of the plurality of the target images to a second set of the plurality of the target images to adapt to the second primary vision area of the target user.

### Claim 3 (depends on 1)

The image display method according to claim 1, wherein the light splitting element is provided with a light splitting area and a through hole area; and emitting, by the light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of target images from different viewing angle comprises:
emitting, by the light splitting area of the light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of the target images from different viewing angles.

### Claim 4 (depends on 3)

The image display method according to claim 3, wherein after emitting, by light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of the target images from different viewing angle, the method further comprises:
displaying a target picture in a target image from the plurality of target images through the through hole area of the light splitting element, comprising:
acquiring a plurality of display parameters comprising: a resolution and a content type;
acquiring an image picture in the target image that satisfies the plurality of display parameters to obtain the target picture; and
displaying the target picture through the through hole area of the light splitting element.

### Claim 5 (depends on 1)

The image display method according to claim 1, wherein before performing the image analysis on the original image according to the pre-set image analysis model to obtain the target depth map, the method further comprises:
training a neural network model to obtain the image analysis model, comprising:
acquiring an image training data set and a loss function; and
training the neural network model according to the loss function and the image training data set to obtain the image analysis model.

### Claim 6

An image display device, comprising:
an acquisition module, configured to acquire an original image;
an analysis module, configured to perform image analysis on the original image according to a pre-set image analysis model to obtain a target depth map;
a synthesis module, configured to perform image synthesis on the target depth map according to a pre-set virtual viewpoint synthesis algorithm to obtain a plurality of target images from different viewing angles, wherein each of the plurality of target images has a respective one of multiple view angles;
a collection module, configured to collect the plurality of the target images from different viewing angles to obtain a target image set; and
a light splitting element, configured to emit each of the plurality of target images in the target image set to a respective one of multiple directions to display the plurality of the target images from different viewing angles.

### Claim 7 (depends on 6)

The image display device according to claim 6, wherein the acquisition module, the analysis module, the synthesis module, and the collection module are integrated in an image processing terminal device, and the light splitting element comprises: a grating screen and a housing, and wherein the grating screen is carried on the housing, the housing is sleeved on the image processing terminal, and the housing is adapted to the image processing terminal device.

### Claim 8 (depends on 7)

The image display device according to claim 7, wherein the image processing terminal device is provided with a first image collector, the housing defines an opening corresponding to the first image collector, the housing is provided with a through hole area, and the housing is provided with a plurality of second image collectors, at least one of the plurality of second image collectors is located on a side of the grating screen, and the rest of the plurality of second image collectors are located on an opposite side of the grating screen.

### Claim 9

An electronic equipment, comprising:
at least one processor, and,
a memory communicatively connected to the at least one processor; wherein
the memory stores an instruction executable by the at least one processor, and the instruction, when executed by the at least one processor, causes the at least one processor to execute an image display method, comprising:
acquiring an original image:
performing image analysis on the original image according to a pre-set image analysis model to obtain a target depth map;
performing image synthesis on the target depth map according to a pre-set virtual viewpoint synthesis algorithm to obtain a plurality of target images from different viewing angles, wherein each of the plurality of target images has a respective one of multiple viewing angles:
collecting the plurality of the target images to obtain a target image set; and
emitting, by a light splitting element, each of the plurality of the target images in the target image set to a respective one of multiple directions to display the plurality of the target images from different viewing angles, such that a target user in a first position with a first primary vision area and a corresponding first viewing angle information views a first set of the plurality of the target images.

### Claim 10 (depends on 1)

A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable instruction, and the computer-executable instruction, when executed by a computer, causes the computer to execute the method according to claim 1.

### Claim 11 (depends on 2)

The image display method according to claim 2, wherein before performing the image analysis on the original image according to the pre-set image analysis model to obtain the target depth map, the method further comprises:
training a neural network model to obtain the image analysis model, comprising:
acquiring an image training data set and a loss function; and
training the neural network model according to the loss function and the image training data set to obtain the image analysis model.

### Claim 12 (depends on 3)

The image display method according to claim 3, wherein before performing the image analysis on the original image according to the pre-set image analysis model to obtain the target depth map, the method further comprises:
training a neural network model to obtain the image analysis model, comprising:
acquiring an image training data set and a loss function; and
training the neural network model according to the loss function and the image training data set to obtain the image analysis model.

### Claim 13 (depends on 4)

The image display method according to claim 4, wherein before performing the image analysis on the original image according to the pre-set image analysis model to obtain the target depth map, the method further comprises:
training a neural network model to obtain the image analysis model, comprising:
acquiring an image training data set and a loss function; and
training the neural network model according to the loss function and the image training data set to obtain the image analysis model.

### Claim 14 (depends on 9)

The electronic equipment according to claim 9, wherein both a current primary vision area and current viewing angle information of the target user change with a position where the target user is located, after emitting, by the light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of the target images from different viewing angles, the method further comprises:
adjusting a target image displayed in the current primary vision area of the target user, comprising:
in response to the target user moving to a second position from the first position, acquiring second viewing angle information of the target user as the current viewing angle information;
determining a second primary vision area corresponding to the second viewing angle information as the current primary vision area of the target user according to the second viewing angle information; and
switching the first set of the plurality of the target images to a second set of the plurality of the target images to adapt to the second primary vision area of the target user.

### Claim 15 (depends on 9)

The electronic equipment according to claim 9, wherein the light splitting element is provided with a light splitting area and a through hole area; and emitting, by the light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of target images from different viewing angle comprises:
emitting, by the light splitting area of the light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of the target images from different viewing angles.

### Claim 16 (depends on 15)

The electronic equipment according to claim 15, wherein after emitting, by light splitting element, each of the plurality of target images in the target image set to the respective one of multiple directions to display the plurality of the target images from different viewing angle, the method further comprises:
displaying a target picture in a target image from the plurality of target images through the through hole area of the light splitting element, comprising:
acquiring a plurality of display parameters comprising: a resolution and a content type;
acquiring an image picture in the target image that satisfies the plurality of display parameters to obtain the target picture; and
displaying the target picture through the through hole area of the light splitting element.

### Claim 17 (depends on 2)

A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable instruction, and the computer-executable instruction, when executed by a computer, causes the computer to execute the method according to claim 2.

### Claim 18 (depends on 3)

A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable instruction, and the computer-executable instruction, when executed by a computer, causes the computer to execute the method according to claim 3.

### Claim 19 (depends on 4)

A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable instruction, and the computer-executable instruction, when executed by a computer, causes the computer to execute the method according to claim 4.

### Claim 20 (depends on 5)

A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable instruction, and the computer-executable instruction, when executed by a computer, causes the computer to execute the method according to claim 5.
