18368921. METHOD PERFORMED BY ELECTRONIC APPARATUS, ELECTRONIC APPARATUS AND STORAGE MEDIUM simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

METHOD PERFORMED BY ELECTRONIC APPARATUS, ELECTRONIC APPARATUS AND STORAGE MEDIUM

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Xiansong Song of Beijing (CN)

Lei Cao of Beijing (CN)

Li Zuo of Beijing (CN)

Jaekeun Na of Suwon-si (KR)

Wei Wen of Beijing (CN)

Changwei Wang of Beijing (CN)

Mengmeng Bai of Beijing (CN)

METHOD PERFORMED BY ELECTRONIC APPARATUS, ELECTRONIC APPARATUS AND STORAGE MEDIUM - A simplified explanation of the abstract

This abstract first appeared for US patent application 18368921 titled 'METHOD PERFORMED BY ELECTRONIC APPARATUS, ELECTRONIC APPARATUS AND STORAGE MEDIUM

Simplified Explanation

The method described in the abstract involves processing video frames to remove objects from the scene. Here is a simplified explanation of the patent application:

  • Determining a local frame sequence from a video
  • Obtaining a feature map sequence by encoding the local frame sequence
  • Determining a feature flow sequence based on the feature map sequence and a mask image sequence
  • Obtaining an updated feature map sequence by performing feature fusion between adjacent feature maps
  • Obtaining a processed local frame sequence by decoding the updated feature map sequence

Potential Applications

This technology could be applied in video editing software to remove unwanted objects from videos, such as logos or people, without the need for manual editing.

Problems Solved

This technology solves the problem of removing objects from videos in a more efficient and automated way, saving time and effort for video editors.

Benefits

The benefits of this technology include faster video editing processes, improved video quality, and the ability to remove objects seamlessly from videos.

Potential Commercial Applications

A potential commercial application of this technology could be in the development of video editing software for professionals and amateurs alike, looking to enhance their videos by removing unwanted objects.

Possible Prior Art

One possible prior art for this technology could be existing video editing software that offers object removal tools, but may not use the same advanced feature fusion techniques described in this patent application.

Unanswered Questions

How does this technology handle complex backgrounds in videos?

The technology described in the patent application focuses on removing objects from videos, but it is unclear how it handles complex backgrounds with intricate details and textures.

What is the computational cost of implementing this technology in real-time video processing?

While the abstract mentions encoding, decoding, and feature fusion processes, it does not provide information on the computational resources required to implement this technology for real-time video processing.


Original Abstract Submitted

A method performed by an electronic apparatus, includes: determining a local frame sequence from a video; obtaining a feature map sequence of the local frame sequence by encoding the local frame sequence; determining a feature flow sequence of the local frame sequence based on the feature map sequence of the local frame sequence and a mask image sequence regarding an object to be removed, the mask image sequence being corresponding to the feature map sequence; obtaining an updated feature map sequence of the local frame sequence, by performing, based on the feature flow sequence, feature fusion between adjacent feature maps in the feature map sequence; and obtaining a processed local frame sequence, by decoding the updated feature map sequence of the local frame sequence.