17938013. SYSTEM AND METHOD FOR MOTION WARPING USING MULTI-EXPOSURE FRAMES simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR MOTION WARPING USING MULTI-EXPOSURE FRAMES

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Anqi Yang of Plano TX (US)

John W. Glotzbach of Allen TX (US)

Hamid R. Sheikh of Allen TX (US)

SYSTEM AND METHOD FOR MOTION WARPING USING MULTI-EXPOSURE FRAMES - A simplified explanation of the abstract

This abstract first appeared for US patent application 17938013 titled 'SYSTEM AND METHOD FOR MOTION WARPING USING MULTI-EXPOSURE FRAMES

Simplified Explanation

The patent application describes a method for improving image quality by using multiple image frames with different exposure times. The method involves obtaining a first image frame and multiple second image frames of a scene using an electronic device's image sensor.

  • The second image frames have different exposure times compared to the first image frame.
  • Blur kernels, which indicate the motion direction of the first image frame, are generated using an optical flow network.
  • The blur kernels are further refined using a convolutional neural network.
  • A target image frame of the scene is generated using the refined blur kernels and occlusion masks for the second image frames.

Potential applications of this technology:

  • Improving image quality in low-light conditions by combining multiple frames with different exposure times.
  • Enhancing image stabilization by analyzing motion direction and refining blur kernels.
  • Creating high-quality images by reducing motion blur and occlusion effects.

Problems solved by this technology:

  • Overcoming limitations of single-frame image capture by utilizing multiple frames with different exposure times.
  • Addressing motion blur and occlusion issues in image processing.
  • Improving image quality in challenging lighting conditions.

Benefits of this technology:

  • Enhanced image quality with reduced motion blur and improved exposure.
  • Improved image stabilization for clearer and sharper images.
  • Increased versatility in capturing high-quality images in various lighting conditions.


Original Abstract Submitted

A method includes obtaining, using at least one image sensor of an electronic device, a first image frame and multiple second image frames of a scene. Each of the second image frames has an exposure time different from an exposure time of the first image frame. The method also includes generating, using at least one processor, blur kernels indicating a motion direction of the first image frame using an optical flow network. The method further includes refining, using the at least one processor, the blur kernels using a convolutional neural network. In addition, the method includes generating, using the at least one processor, a target image frame of the scene using the refined blur kernels and occlusion masks for the second image frames.