Qualcomm incorporated (20240242309). SUPER RESOLUTION BASED ON SALIENCY simplified abstract
SUPER RESOLUTION BASED ON SALIENCY
Organization Name
Inventor(s)
Weixing Wan of Baoshan District, Shanghai (CN)
SUPER RESOLUTION BASED ON SALIENCY - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240242309 titled 'SUPER RESOLUTION BASED ON SALIENCY
- Simplified Explanation:**
The patent application describes a system for image processing that can enhance the resolution of specific regions within an image.
- Key Features and Innovation:**
- Imaging system can identify salient regions in an image and increase their resolution using different processes.
- First process involves using a trained network to modify the more salient region to a higher resolution.
- Second process utilizes interpolation to enhance the resolution of less salient regions.
- Output image includes both modified regions at increased resolutions.
- Potential Applications:**
This technology can be used in various fields such as medical imaging, satellite imagery, surveillance systems, and photography.
- Problems Solved:**
The system addresses the issue of enhancing image resolution selectively in specific regions rather than applying a uniform enhancement across the entire image.
- Benefits:**
- Improved image quality by selectively increasing resolution in important regions.
- Enhanced visual clarity and detail in critical areas of an image.
- Efficient use of computational resources by focusing on salient regions.
- Commercial Applications:**
The technology can be applied in industries such as healthcare, security, remote sensing, and digital photography to enhance image quality and detail in key areas.
- Questions about Image Processing:**
1. How does the system determine which regions of the image are more salient than others? 2. What are the potential limitations of using interpolation to increase the resolution of less salient regions?
Original Abstract Submitted
systems and techniques are described for image processing. for instance, an imaging system can obtain an input image with a first region and a second region, both at a first resolution. the imaging system can determine that the first region is more salient than the second region (e.g., based on a saliency map mapping saliency values to pixels of the input image). the imaging system can use a first process (e.g., using a trained network, such as of a machine learning super resolution system) to modify the first region to increase the first resolution to a second resolution. the imaging system can use a second process (e.g., based on an interpolation process) to modify the second region to increase the first resolution of the second region to the second resolution. the imaging system can generate and/or output an output image including the modified first region and the modified second region.