Virtual Viewpoint Image Generation Across Multiple Formats

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing virtual viewpoint image generation techniques only provide content in a common format, lacking the ability to offer diverse formats such as 2D, 3D, panorama, and 3D panorama, which limits user experience and satisfaction.

Innovation Solution

An information processing system and method that generates and distributes virtual viewpoint contents in various formats by using multiple imaging devices to capture images from different viewpoints, allowing users to designate arbitrary viewing points and orientations, and employing a server system to process and output images according to specified projection schemes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If virtual viewpoint images are generated in a common format only, then the system complexity is reduced and processing is simplified, but the adaptability to different user preferences and viewing requirements deteriorates

Engineering Contradiction:
Improveformat diversityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The image generation server is designed to perform multiple functions by supporting various projection schemes (2D, 3D, panorama, 3D panorama) within a single system. The server can generate virtual viewpoint images in different formats based on user requests, making one system capable of serving multiple format requirements without needing separate systems for each format

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system changes the projection scheme parameter to generate different image formats. By modifying the projection scheme parameter (2D, 3D, panorama, 3D panorama), the same image generation server can produce various formats of virtual viewpoint images from the same multi-viewpoint image data, enabling format diversity without increasing fundamental system complexity

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If multiple imaging devices are used to capture images from different viewpoints, then the quality and versatility of virtual viewpoint contents are improved, but the device complexity and processing requirements increase

Engineering Contradiction:
Improveimage qualityVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system segments the image processing task by first capturing multi-viewpoint images from multiple imaging devices, then using an image generation server to process these segmented views into different projection schemes. The segmentation allows each camera to focus on capturing high-quality images from its specific viewpoint, while the server handles the complex task of combining and transforming these views into various formats

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3882866B1Information processing system, information processing method, and program
Publication Date: 2024.05.15 CANON KK
  • EP3882866B1 patent drawingFigure 1
  • EP3882866B1 patent drawingFigure 2
  • EP3882866B1 patent drawingFigure 3(a)~3(b)

AI summary

The information processing system according to the present invention includes: an image acquisition unit configured to acquire a plurality of images based on image capturing by a plurality of imaging devices capturing a target area from directions different from one another; a viewpoint acquisition unit configured to acquire viewpoint information indicating a position and orientation of a virtual viewpoint; and a generation unit configured to generate a plurality of virtual viewpoint contents corresponding to a plurality of image formats based on the common plurality of images acquired by the image acquisition unit and the viewpoint information acquired by the viewpoint acquisition unit, and the plurality of image formats is image formats whose numbers of virtual viewpoints indicated by the viewpoint information used for generation of the virtual viewpoint contents are different from one another.