VR Memory Allocation via Spatial Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Virtual Reality (VR) technologies face challenges in real-time rendering performance due to high storage requirements exceeding graphics processing unit (GPU) memory capacity, leading to potential lags and latencies in immersive content presentation.

Innovation Solution

The system allocates memory by transferring a first dataset of media content to GPU memory and identifying a second dataset based on the user's location and time code status, ensuring seamless presentation by provisioning GPU memory with necessary data, supporting an arbitrary number of viewpoints for 3D scene reconstruction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If high-fidelity VR content is stored in full resolution, then content quality is improved, but memory capacity requirements exceed GPU capabilities

Engineering Contradiction:

Improvecontent qualityVSAvoidmemory capacity

Core Design Contradiction:

Manufacturing precisionVSQuantity of substance

Solution Approach 1:

The VR content is divided into multiple resolution versions (full resolution and lower resolution). The system segments the content based on spatial importance, storing only critical portions in full resolution in GPU memory while keeping less important portions in lower resolution in host memory, thereby reducing memory capacity requirements while maintaining perceived quality.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different regions of the VR content are assigned different quality levels based on their importance. The system identifies and prioritizes important regions (such as areas containing critical visual information) for full resolution rendering, while allowing less important regions to be rendered at lower resolutions, optimizing the balance between content quality and memory usage.

Inventive Principle:

Principle #3Local quality

2Ease of operation

If all VR content is loaded into GPU memory, then content accessibility is improved, but data transfer bandwidth requirements increase

Engineering Contradiction:

Improvecontent accessibilityVSAvoiddata transfer bandwidth

Core Design Contradiction:

Ease of operationVSLoss of energy

Solution Approach 1:

The system performs preliminary identification of important regions in the VR content before rendering. By pre-processing the content to determine which regions require full resolution, the system can load only those critical regions into GPU memory in advance, avoiding the need to transfer all content data and reducing bandwidth requirements while maintaining accessibility of essential content.

Inventive Principle:

Principle #10Preliminary action

3Manufacturing precision

If full resolution VR content is rendered in real-time, then rendering quality is improved, but real-time rendering performance decreases

Engineering Contradiction:

Improverendering qualityVSAvoidreal-time rendering performance

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The rendering process is segmented by spatial importance rather than uniformly processing all content at full resolution. The system identifies important regions and renders only those at full resolution in real-time, while other regions are rendered at lower resolutions or pre-processed, thereby maintaining rendering quality for critical areas while achieving real-time performance requirements.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies different rendering quality levels to different spatial regions based on their importance. Important regions receive full resolution real-time rendering to maintain high quality, while less important regions use lower resolution rendering, optimizing the balance between rendering quality and real-time performance.

Inventive Principle:

Principle #3Local quality

4Quantity of substance

If VR content is compressed to reduce storage requirements, then storage capacity is improved, but content fidelity deteriorates

Engineering Contradiction:

Improvestorage capacityVSAvoidcontent fidelity

Core Design Contradiction:

Quantity of substanceVSManufacturing precision

Solution Approach 1:

The content is segmented into different resolution versions with varying fidelity levels. Critical portions of the content are maintained in full resolution with high fidelity, while less critical portions are compressed to lower resolutions. This selective segmentation allows the system to reduce overall storage requirements while preserving content fidelity where it matters most.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10482570B2Memory allocation for seamless media content presentation

Publication Date: 2019.11.19 DISNEY ENTERPRISES INC

AI summary

A system for performing memory allocation for seamless media content presentation includes a computing platform having a CPU, a GPU having a GPU memory, and a main memory storing a memory allocation software code. The CPU executes the memory allocation software code to transfer a first dataset of media content to the GPU memory, seamlessly present the media content to a system user, register a location of the system user during the seamless presentation of the media content, and register a timecode status of the media content at the location. The CPU further executes the memory allocation software code to identify a second dataset of the media content based on the location and the timecode status, transfer a first differential dataset to the GPU memory, continue to seamlessly present the media content to the system user, and transfer a second differential dataset out of the GPU memory.