18159509. ADAPTIVE ZOOM TRY-ON EXPERIENCE simplified abstract (Snap Inc.)

ADAPTIVE ZOOM TRY-ON EXPERIENCE

Organization Name

Snap Inc.

Inventor(s)

Matan Zohar of Rishon LeZion (IL)

Omri Berg of Tel Aviv (IL)

Gal Sasson of Kibbutz Ayyelet Hashahar (IL)

Itamar Berger of Hod Hasharon (IL)

ADAPTIVE ZOOM TRY-ON EXPERIENCE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18159509 titled 'ADAPTIVE ZOOM TRY-ON EXPERIENCE

Simplified Explanation: The system automatically zooms in on fashion items worn by a person in a video frame, extracts a portion of the item, generates a focus image, and presents it with the video.

Key Features and Innovation:

• Automatic zooming on fashion items in videos
• Extraction of fashion item portions from frames
• Generation of focus images for presentation
• Integration of focus images with videos

Potential Applications: This technology can be used in fashion industry for product showcasing, in video editing for enhancing details, and in e-commerce for improving product visibility.

Problems Solved: This technology addresses the challenge of focusing on specific fashion items in videos, enhancing the viewing experience, and increasing the visibility of products.

Benefits:

• Improved focus on fashion items
• Enhanced visual presentation
• Increased product visibility
• Better user experience

Commercial Applications: The technology can be utilized in online fashion platforms, video editing software, and e-commerce websites to enhance product showcasing and user engagement.

Prior Art: Prior art related to this technology can be found in the fields of computer vision, image processing, and video analysis.

Frequently Updated Research: Research on improving the accuracy and efficiency of automatic zooming algorithms in videos is ongoing in the field of computer vision.

Questions about Automatic Zooming Technology: 1. How does the system determine which fashion item to zoom in on in a video? 2. What are the potential privacy implications of automatically zooming in on individuals in videos?

2. How does the system ensure accurate extraction of fashion item portions from video frames? 4. What are the limitations of automatic zooming technology in videos? 5. How can this technology be further improved for commercial applications?

Original Abstract Submitted

Aspects of the present disclosure involve a system for automatically zooming in on objects in an image. The system accesses a video comprising a frame depicting a person and detects a fashion item being worn by the person in the frame of the video. The system, in response to detecting the fashion item being worn by the person, extracts, from the frame, a portion comprising a depiction of the fashion item being worn by the person. The system generates a focus image of the fashion item using the portion extracted from the frame and presents the focus image of the fashion item together with the video comprising the frame depicting the person.