Object-Mask Image Editing With Inpainting and Outpainting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices lack advanced image editing capabilities, particularly in reconfiguring images using generative AI to change object positions, sizes, angles, and backgrounds, and adding or removing objects, which limits user creativity and composition control.
Innovation Solution
An electronic device equipped with a display, communication circuit, processor, and memory that supports image editing through user inputs for selecting, cropping, and moving objects, generating masking areas, and applying AI-based inpainting or outpainting to enhance image composition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional image editing methods are used, then basic cropping and moving functions are available, but advanced capabilities for reconfiguring images (changing object positions, sizes, angles, backgrounds, adding/removing objects) are lacking
Solution Approach 1:
The patent introduces a masking area as an intermediary element between the cropped object and the background. This masking area enables sophisticated operations like selective background replacement, object repositioning, and generative AI-based inpainting without requiring direct manipulation of complex image data, thus enhancing editing versatility while managing system complexity through abstraction
Solution Approach 2:
The patent segments the image into distinct components: cropped objects, masking areas, and background regions. This segmentation allows independent manipulation of each component (moving objects, replacing backgrounds, adjusting sizes) and enables the system to handle complex editing tasks through simpler, modular operations on individual segments
2Adaptability or versatility
If generative AI-based image reconfiguration is implemented, then user creativity and composition control are enhanced, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by first cropping objects and generating masking areas before applying generative AI-based inpainting or outpainting. This preparatory segmentation and masking reduces the computational burden on the generative AI model, as it only needs to process the specific masked regions rather than entire images, thereby reducing processing time while maintaining reconfiguration capabilities
Solution Approach 2:
The patent applies generative AI processing locally to specific masking areas rather than entire images. By confining the computationally intensive inpainting/outpainting operations to only the regions requiring reconfiguration (masked areas), the system achieves high-quality local image generation while minimizing overall processing time and computational resource consumption
3Ease of operation
If multiple editing handlers and masking areas are introduced, then precise control over object positions and compositions is achieved, but user interface complexity increases
Solution Approach 1:
The patent implements feedback mechanisms where the system continuously updates the display to show the relationship between cropped objects, masking areas, and the overall image composition. This visual feedback allows users to precisely control object positions and compositions by providing real-time information about how editing actions affect the final result, making the interface more intuitive despite the presence of multiple handlers and masking areas
Data Source
AI summary
An electronic device is provided. The electronic device includes, a display, a communication circuit, at least one processor including processing circuitry, and memory configured to store instructions, wherein the instructions, when individually and/or collectively executed by the at least one processor, cause the electronic device to display an image on the display, receive a first input of selecting a part corresponding to an object in the image, crop the part corresponding to the object in the image, based on the first input, detect a second input of moving the cropped part from an original location in the image, configure and display, as a masking area, an area corresponding to the original location of the cropped part in the image, based on movement of the cropped part, receive a third input of selecting one of the cropped part or the masking area, in case that the third input corresponds to selecting the cropped part, provide a first handler related to editing of the cropped part through the cropped part, in case that the third input corresponds to selecting the masking area, provide a second handler related to editing of the cropped part through the masking area, edit the image in response to a fourth input received based on the first handler or the second handler, based on a fifth input, generate an instruction causing inpainting and/or outpainting to be performed based on the edited image, obtain a result image in relation to the instruction, and display the result image via the display.