18332939. METHOD AND APPARATUS WITH FRAME IMAGE RECONSTRUCTION simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

METHOD AND APPARATUS WITH FRAME IMAGE RECONSTRUCTION

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Hyeonseung Yu of Suwon-si (KR)

Nahyup Kang of Suwon-si (KR)

Hanjun Kim of Suwon-si (KR)

Jaeyoung Moon of Suwon-si (KR)

Juyoung Lee of Suwon-si (KR)

Hwiryong Jung of Suwon-si (KR)

Inwoo Ha of Suwon-si (KR)

Seokpyo Hong of Suwon-si (KR)

METHOD AND APPARATUS WITH FRAME IMAGE RECONSTRUCTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18332939 titled 'METHOD AND APPARATUS WITH FRAME IMAGE RECONSTRUCTION

The abstract of the patent application describes a method involving the generation of a semantic map indicating visualization properties assigned to objects in a frame image, followed by the generation of a reconstruction image using a machine learning model based on the frame image and semantic map.

• Semantic map generated to indicate visualization properties of objects in a frame image
• Reconstruction image created using machine learning model based on frame image and semantic map
• Reconstruction image includes objects with visualization properties indicated by the semantic map

Potential Applications: - Image processing and analysis - Computer vision applications - Augmented reality systems

Problems Solved: - Enhancing image reconstruction accuracy - Improving object visualization in images - Streamlining machine learning model input generation

Benefits: - Enhanced image reconstruction quality - Improved object recognition in images - Streamlined machine learning model training process

Commercial Applications: - Image editing software - Surveillance systems - Medical imaging technology

Questions about the technology: 1. How does the semantic map improve the accuracy of object visualization in the reconstruction image? 2. What are the potential real-world applications of this technology beyond image processing and analysis?

Original Abstract Submitted

A processor implemented method includes generating a semantic map indicating a visualization property assigned to an object of an obtained frame image having a first resolution and generating a reconstruction image using an image reconstruction machine learning model provided input based on the obtained frame image and the semantic map having a second resolution and including a second object having a visualization property indicated by the semantic map.