MPI Layer Geometry Using Pixel Ray Crossing for Random View Rendering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing MPI-based methods suffer from image distortion due to geometric segmentation phenomena during rendering, which affects the quality of random viewpoint rendering.

Innovation Solution

A pixel ray crossing-based multi-viewpoint MPI geometry generation method that projects pixel positions onto MPI layer planes based on camera positions and spatial coordinates, using RGB and Alpha images to configure an atlas image and encode it into a bitstream, thereby avoiding geometric segmentation distortion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If existing MPI layer configuration method considering only geometric information is used, then the device complexity is reduced, but image distortion occurs due to geometric segmentation phenomenon

Engineering Contradiction:

ImproveMPI layer configuration complexityVSAvoidimage quality

Core Design Contradiction:

Device complexityVSManufacturing precision

Solution Approach 1:

The patent changes the projection parameters by introducing camera position coordinates and ray crossing calculations. Instead of simple geometric projection, the system calculates precise pixel positions by determining where rays from different camera viewpoints intersect with MPI layer planes, using parameters including camera positions, layer plane distances, and world coordinate system transformations

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary calculation process involving ray crossing computations. The system uses intermediate variables such as ray direction vectors, intersection points, and coordinate transformations to bridge the gap between simple geometric projection and accurate multi-viewpoint rendering, thereby eliminating geometric segmentation distortion

Inventive Principle:

Principle #24Intermediary (Mediator)

2Manufacturing precision

If pixel ray crossing-based projection is used, then image quality is improved by avoiding geometric segmentation distortion, but device complexity increases

Engineering Contradiction:

Improveimage qualityVSAvoidprojection calculation complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent segments the projection process into distinct computational stages: (1) defining camera positions and world coordinate systems, (2) calculating ray directions from camera pixels through scene points, (3) determining ray intersections with MPI layer planes, and (4) mapping intersection points to pixel positions. This segmentation makes the complex calculation process more manageable and implementable

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from 2D image plane coordinates to 3D world coordinate systems and back to 2D layer plane coordinates. By introducing the third dimension (depth/distance from camera) and using ray crossing in 3D space, the system achieves accurate multi-viewpoint rendering that eliminates geometric segmentation distortion while maintaining computational feasibility

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS12548230B2MPI layer geometry generation method using pixel ray crossing

Publication Date: 2026.02.10 ELECTRONICS & TELECOMM RES INST

AI summary

A pixel ray crossing-based multi-viewpoint MPI geometry generation method, device, and recording medium of the present disclosure, the method may comprise obtaining a multi-viewpoint image by original cameras which shoot a different viewpoint, obtaining a multi-plane image (MPI) based on the multi-viewpoint image, obtaining, based on the MPI, an atlas image in a 2D form, and obtaining a bitstream by encoding the atlas image.