17718661. METHOD AND APPARATUS FOR IMAGE RESTORATION BASED ON BURST IMAGE simplified abstract (Samsung Electronics Co., Ltd.)
Contents
METHOD AND APPARATUS FOR IMAGE RESTORATION BASED ON BURST IMAGE
Organization Name
Inventor(s)
Jae Seok Choi of Suwon-si (KR)
Sanghyun Kim of Pohang-si (KR)
Hyong Euk Lee of Suwon-si (KR)
METHOD AND APPARATUS FOR IMAGE RESTORATION BASED ON BURST IMAGE - A simplified explanation of the abstract
This abstract first appeared for US patent application 17718661 titled 'METHOD AND APPARATUS FOR IMAGE RESTORATION BASED ON BURST IMAGE
Simplified Explanation
The patent application describes a method and apparatus for image restoration using burst images. Here are the key points:
- The method involves encoding individual images of a burst image set to generate a plurality of feature representations.
- A reference feature representation is determined from the generated feature representations.
- A first comparison pair is determined, consisting of the reference feature representation and a first feature representation.
- A first motion-embedding feature representation is generated for the first comparison pair based on a similarity score map.
- Multiple motion-embedding feature representations are fused together to generate a fusion result.
- The fusion result is decoded to generate at least one restored image.
Potential applications of this technology:
- Image restoration in photography: This technology can be used to enhance the quality of images captured in burst mode, improving details and reducing noise.
- Forensic analysis: The method can help in restoring and enhancing images from surveillance cameras or crime scene photographs, aiding in investigations.
- Medical imaging: The technology can be applied to restore and improve the quality of medical images, assisting in accurate diagnosis and treatment.
Problems solved by this technology:
- Image quality improvement: The method addresses the challenge of restoring and enhancing images captured in burst mode or under challenging conditions, resulting in improved image quality.
- Noise reduction: By fusing multiple motion-embedding feature representations, the technology helps in reducing noise and artifacts in the restored images.
Benefits of this technology:
- Enhanced image details: The method improves the level of details in the restored images, making them clearer and more visually appealing.
- Noise reduction: By effectively fusing multiple feature representations, the technology helps in reducing noise and artifacts, resulting in cleaner images.
- Versatility: The method can be applied to various types of images, including those captured in burst mode or under challenging conditions, making it a versatile solution for image restoration.
Original Abstract Submitted
A method and apparatus for image restoration based on burst images. The method includes generating a plurality of feature representations corresponding to individual images of a burst image set by encoding the individual images, determining a reference feature representation from among the plurality of feature representations, determining a first comparison pair including the reference feature representation and a first feature representation of the plurality of feature representations, generating a first motion-embedding feature representation of the first comparison pair based on a similarity score map of the reference feature representation and the first feature representation, generating a fusion result by fusing a plurality of motion-embedding feature representations including the first motion-embedding feature representation, and generating at least one restored image by decoding the fusion result.
