EP-4742194-A1 - METHOD AND APPARATUS FOR GENERATING IMAGE, DEVICE AND PRODUCT

EP4742194A1EP 4742194 A1EP4742194 A1EP 4742194A1EP-4742194-A1

Abstract

The present disclosure relates to a method and an apparatus for generating an image, a device, and a product. The method (300) includes: determining (302) a plurality of corresponding image layers based on images of interior and exterior environments of a vehicle, where spatial relationships of the plurality of image layers are different. The method (300) further includes generating (304), by an image generation model and based on the plurality of image layers, a corresponding image according to a status of a vehicle and/or information input by a user. In this way, in conjunction with a user input, a vehicle status, and surroundings of the vehicle, an image matching the user's intention and the vehicle environment can be generated, which can improve the user experience.

Inventors

LIN, NAN
LIU, YANG
WANG, Liyao
DUAN, Ning

Assignees

Cariad (China) Co., Ltd.

Dates

Publication Date: 20260513
Application Date: 20251105

Claims (15)

A method (300) for generating an image, comprising: determining (302), based on images of an interior and exterior environment of a vehicle, a plurality of corresponding image layers, spatial relationships of the plurality of image layers being different; generating (304), by an image generation model and based on the plurality of image layers, a corresponding image based on a status of the vehicle and/or information input by a user.
The method of claim 1, wherein determining (302), based on the images of the interior and exterior environment of the vehicle, the plurality of corresponding image layers comprises: obtaining, using a plurality of image acquisition devices, an environment image of surroundings of the vehicle, and an interior image of the vehicle corresponding to an interior of the vehicle; determining, based on the interior image corresponding to the interior of the vehicle, a person image corresponding to a user inside the vehicle; and generating the plurality of corresponding image layers based on the environment image, the interior image of the vehicle, and the person image corresponding to the user.
The method of claim 2, wherein determining (302) the plurality of corresponding image layers comprises: determining, based on identification information of the plurality of image acquisition devices, a plurality of sub-environment images for a plurality of directions in the environment image, the directions comprising one or more of: front, rear, left, and right of the vehicle; and determining the plurality of corresponding image layers based on the plurality of sub-environment images, the interior image of the vehicle, and the person image.
The method of claim 2 or 3, wherein generating (304), by the image generation model and based on the plurality of image layers, the corresponding image comprises: generating, based on the plurality of image layers, a plurality of corresponding candidate image layers; determining, based on the status of the vehicle and/or the information input by the user, a target image layer to be adjusted of the plurality of candidate image layers; and adjusting, by the image generation model, the target image layer, to generate the corresponding image.
The method of claim 4, wherein adjusting the target image layer comprises: determining a type corresponding to the person image, and an image feature corresponding to the person image; and adjusting the target image layer based on the type and the image feature, the target image layer comprising at least one image layer of a person image layer, or an environment image layer.
The method of claim 5, wherein adjusting the target image layer further comprises: adjusting, based on the image feature, a person feature of the person image layer of the at least one image layer, wherein a person feature corresponding to the adjusted person image layer matches the image feature that comprises a facial feature, and a pose feature of a person; and adjusting, based on the image feature, an environment feature in an image layer of the interior environment of the vehicle.
The method of any one of claims 4 to 6, wherein adjusting the target image layer comprises: determining, based on the information input by the user, a corresponding key element and a corresponding image style; and adjusting the target image layer based on the key element and the image style.
The method of any one of claims 4 to 7, wherein adjusting the target image layer comprises: obtaining environment information corresponding to the vehicle, the environment information comprising weather information, time information and geographic location information; and adjusting the target image layer based on the environment information, the status of the vehicle, and the information input by the user.
The method of any one of claims 1 to 8, further comprising: obtaining traveling data, driving data, media resource data, and corresponding vehicle control unit data of the vehicle; and determining the status of the vehicle based on the traveling data, the driving data, the media resource data, and the vehicle control unit data.
The method of any one of claims 4 to 8, wherein generating (304) the corresponding image comprises: determining a corresponding fused image by performing fusion of multi-image layers on adjusted image layers, to determine a corresponding fused image; and generating, by the image generation model, the corresponding image based on the fused image.
The method of claim 10, wherein determining the corresponding fused image comprises: determining edge information corresponding to each image layer of the adjusted image layers; determining image layers with adjacent edges based on the edge information; and determining the corresponding fused image by fusing the image layers with the adjacent edges.
The method of any one of claims 4 to 8, wherein adjusting the target image layer comprises: generating, by a language model, a text description corresponding to the images of the interior and exterior environment of the vehicle; and adjusting the target image layer based on the text description; wherein the method in particular further comprises: obtaining historical input information of the user for a historical image; and adjusting the target image layer based on the historical image and the historical input information.
An apparatus (600) for generating an image, comprising: an image layer determining module (602), configured to determine, based on images of an interior and exterior environment of a vehicle, a plurality of corresponding image layers, spatial relationships of the plurality of image layers being different; an image generation module (604), configured to generate, by an image generation model and based on the plurality of image layers, a corresponding image based on a status of the vehicle and/or information input by a user.
An electronic device, comprising: at least one processor; and a memory coupled to the at least one processor and having instructions stored thereon, wherein the instructions, when executed by the at least one processor, cause the electronic device to perform the method of any of claims 1-12.
A computer program product tangibly stored on a computer readable medium and comprising machine executable instructions that, when executed, implement the method of any of claims 1-12.

Description

FIELD The present disclosure generally relates to the technical field of vehicles, and more specifically, to a method and an apparatus for generating an image, a device and a product. BACKGROUND With the rapid development of vehicle technology and artificial intelligence, vehicles have become necessities for people in daily life. During driving, users often come across beautiful scenery, or desire to record the travel mood and feelings at some moments. Meanwhile, text-to-text, text-to-picture and picture-to-picture generation technologies, and the like have been widely applied to vehicles. The users have increasingly higher expectations for entertainment functions of in-vehicle systems. For example, users are particularly fond of personalized, smart image generation services. SUMMARY The embodiments of the present disclosure provide a method and an apparatus for generating an image, a device, and a product. In a first aspect of the present disclosure, there is provided a method for generating an image. The method includes determining a plurality of corresponding image layers based on images of interior and exterior environments of a vehicle, where spatial relationships of the plurality of image layers are different. The method further includes generating, by an image generation model and based on the plurality of image layers, a corresponding image according to a status of a vehicle and/or information input by a user. In a second aspect of the present disclosure, there is provided an apparatus for generating an image. The apparatus includes an image layer determining module configured to determine, based on images of interior and exterior environments of a vehicle, a plurality of corresponding image layers, where spatial relationships of the plurality of image layers are different. The apparatus further includes an image generation module configured to generate, by the image generation model and based on the plurality of image layers, a corresponding image according to a status of a vehicle and/or information input by a user. In a third aspect of the present disclosure, there is provided an electronic device. The electronic device includes: one or more processors; and a memory for storing one or more programs, where the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method provided in the first aspect of the present disclosure. In a fourth aspect of the present disclosure, there is provided a computer readable storage medium. The computer readable storage medium has computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method provided in the first aspect of the present disclosure. In a fifth aspect of the present disclosure, there is provided a computer program product tangibly stored on a computer readable medium and comprising machine executable instructions that, when executed, implement the method provided in the first aspect of the present disclosure. It would be appreciated that this Summary is not intended to identify key features or essential features of the embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become evident through the following description. BRIEF DESCRIPTION OF THE DRAWINGS Through the following detailed description with reference to the accompanying drawings, the above and other objectives, features, and advantages of example embodiments of the present disclosure will become more apparent. In the drawings, the same or similar reference symbols refer to the same or similar elements, where: Fig. 1 illustrates a schematic diagram of an example environment where a plurality of embodiments of the present disclosure can be implemented;Fig. 2 illustrates a schematic diagram of a process of generating an image according to some embodiments of the present disclosure;Fig. 3 illustrates a flowchart of a method for generating an image according to some embodiments of the present disclosure;Fig. 4 illustrates a schematic diagram of determining a plurality of image layers according to some embodiments of the present disclosure;Fig. 5 illustrates a schematic diagram of adjusting a plurality of image layers according to some embodiments of the present disclosure;Fig. 6 illustrates a block diagram of an apparatus for generating an image according to some embodiments of the present disclosure; andFig. 7 illustrates a block diagram of a device that can implement a plurality of embodiments of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS Reference below will be made to the drawings to describe in detail the embodiments of the present disclosure. Although some embodiments disclosed herein are depicted in the drawings, it would be appreciated that the present disclosure can be implemented in various manners and should not be limited