Object-Aware Super-Resolution Control for Image Sharpness

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional super resolution (SR) technology fails to reflect the characteristics of input images fully, particularly in diverse environments, and lacks the ability to segment images into object units or apply post-filtering operations effectively.

Innovation Solution

An electronic device and method that analyze input images to obtain image and object information, generate extended object maps, and combine this information with trained neural networks to enhance image quality through techniques like image sharpening and multi-band filtering, ensuring improved resolution and sharpness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If conventional SR technology is used to convert low-resolution images to high-resolution images, then image resolution is improved, but the ability to reflect input image characteristics and apply object-specific post-filtering is insufficient

Engineering Contradiction:

Improveimage resolutionVSAvoidability to reflect input image characteristics

Core Design Contradiction:

Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

The patent segments the input image into multiple object regions using object detection and generates separate object maps for each detected object. This segmentation enables different post-filtering operations to be applied to different objects based on their specific characteristics, thereby improving the system's adaptability to reflect diverse input image characteristics while maintaining high resolution enhancement.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different post-filtering operations (sharpness enhancement, detail enhancement, noise reduction) to different object regions based on their specific characteristics. By analyzing each object's features and applying tailored filtering operations, the system achieves local optimization that reflects the unique characteristics of each input image region while maintaining overall high resolution quality.

Inventive Principle:

Principle #3Local quality

2Manufacturing precision

If post-filtering operations are applied to enhance image sharpness and quality, then image quality is improved, but the complexity of processing increases

Engineering Contradiction:

Improveimage qualityVSAvoidprocessing complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent performs object detection and generates object maps before applying post-filtering operations. By preparing the object segmentation and characteristic analysis in advance, the system organizes the processing workflow efficiently, allowing multiple filtering operations to be applied systematically to different regions without excessive complexity during the actual quality enhancement phase.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent dynamically selects and applies different post-filtering operations (sharpness enhancement, detail enhancement, noise reduction) based on the specific characteristics of each detected object and region. This dynamic approach allows the system to adapt the processing complexity to the actual needs of each image region, applying more sophisticated operations only where necessary while maintaining simpler processing elsewhere.

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If multiple post-filtering operations are applied to different object regions, then adaptability to input characteristics is improved, but processing time increases

Engineering Contradiction:

Improveadaptability to input characteristicsVSAvoidprocessing time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent divides the image into multiple object regions and processes each region independently with appropriate filtering operations. This segmentation allows parallel processing of different regions, reducing the overall processing time compared to sequential processing of the entire image, while still maintaining high adaptability to the specific characteristics of each object region.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies post-filtering operations selectively to only those regions that require enhancement based on object detection results, rather than applying uniform processing to the entire image. This partial action approach reduces unnecessary processing time while maintaining high adaptability to input characteristics in the regions that actually need enhancement.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20250390987A1Electronic device and control method therefor

Publication Date: 2025.12.25 SAMSUNG ELECTRONICS CO LTD

AI summary

An electronic device and a control method for improving image quality include receiving a first-quality image as an input image; analyzing the input image to obtain image parameter information; detecting an object included in the input image to obtain object information; inputting the input image, the image parameter information, and the object information into a trained neural network model; obtaining a second-quality image having a higher image quality than a first-image quality; and outputting the second-quality image. The method may include generating an extended object map by combining an object map with the image parameter information, where the object map is obtained from the object information. Post-filtering techniques, including multi-band image filtering and applying pixel-wise gain values based on object information, may be performed on the output data from the neural network model to further enhance image quality.