Multi-View Graphics Pipeline Buffering for VR Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Generating multi-view image data for VR applications is inefficient as existing methods require inputting primitive data into the graphics processing pipeline twice, leading to redundant calculations and increased processing time.

Innovation Solution

Processing primitive data to generate multiple position vectors for each vertex, storing this data in a buffer, and then transmitting it to the raster pipeline for each view, allowing for efficient generation of image data by performing view-independent processing only once.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If primitive data is input into the graphics processing pipeline twice to generate two different views, then both views can be generated, but the processing time is approximately doubled due to redundant calculations

Engineering Contradiction:
Improveprocessing timeVSAvoidmulti-view image data generation efficiency
Core Design Contradiction:
Loss of timeVSProductivity

Solution Approach 1:

The patent applies preliminary action by performing view-independent processing of primitive data only once before rasterization, rather than repeating it for each view. The processed primitive data is stored in a buffer and then read multiple times for different view projections, eliminating redundant calculations and reducing processing time while maintaining the ability to generate multiple views efficiently

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent merges the processing of multiple views by combining view-independent operations into a single processing pass. The primitive data is processed once to generate a shared representation that can be used for multiple view projections, consolidating redundant operations and improving overall processing efficiency

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS10068366B2Stereo multi-projection implemented using a graphics processing pipeline
Publication Date: 2018.09.04 NVIDIA CORP
  • US10068366B2 patent drawing
  • US10068366B2 patent drawing
  • US10068366B2 patent drawing

AI summary

A method, computer readable medium, and system are disclosed for generating multi-view image data. The method includes the steps of processing primitive data of a model to generate processed primitive data that includes multiple position vectors for each vertex in the primitive data, the number of position vectors associated with each vertex being equal to the number of views in at least two views being generated. The method further includes storing the processed primitive data in a buffer. Finally, the processed primitive data may be read from the buffer for each view in the at least two views and transmitted to a raster pipeline to generate image data corresponding to a particular view.