Ray Tracing Cache Reuse for Rendering Speed

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Ray tracing methods face challenges in achieving high-speed rendering due to the large number of operations required for generating and traversing acceleration structures and performing intersection tests, which hinders efficient image processing.

Innovation Solution

The method utilizes a traversal cache to store results of previous rays and determines similarity between rays, allowing the ray tracing apparatus to reuse stored results for similar rays, reducing the number of operations needed by extracting feature information, determining a key for the ray, and using this key to retrieve relevant acceleration structure traversal data for improved processing capacity and speed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If ray tracing is used to generate high quality images by tracing light paths through each pixel, then image quality is improved, but the number of operations required for generating and traversing acceleration structures increases, reducing rendering speed

Engineering Contradiction:
Improveimage qualityVSAvoidrendering speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent pre-calculates and stores traversal results of acceleration structures for representative rays in advance. When rendering, instead of traversing the entire acceleration structure for each ray, the system retrieves pre-computed traversal results from memory, significantly reducing the number of operations required during actual rendering while maintaining image quality

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates and stores copies of acceleration structure traversal results for multiple rays in a lookup table. These pre-computed traversal paths are copied into memory and reused during rendering, avoiding repeated traversal operations and thereby improving rendering speed without sacrificing image quality

Inventive Principle:
Principle #26Copying

2Measurement precision

If acceleration structures are generated and traversed for each ray to ensure accurate intersection tests, then rendering accuracy is improved, but the large number of operations required reduces processing capacity and speed

Engineering Contradiction:
Improveintersection test accuracyVSAvoidprocessing capacity
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent performs preliminary traversal of acceleration structures to compute and store intersection results before actual rendering. By pre-calculating which primitives intersect with rays and storing these results, the system eliminates the need to perform full acceleration structure traversals during rendering, thereby maintaining intersection test accuracy while dramatically improving processing capacity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a self-service system where the acceleration structure traversal results are computed once and stored for reuse. The pre-computed traversal data serves itself by being directly retrieved and applied during rendering operations, eliminating redundant computations and thereby improving processing capacity while maintaining accuracy

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP2869273B1Ray tracing method and apparatus
Publication Date: 2022.11.02 SAMSUNG ELECTRONICS CO LTD
  • EP2869273B1 patent drawingFigure 1
  • EP2869273B1 patent drawingFigure 2
  • EP2869273B1 patent drawingFigure 3

AI summary

A ray tracing method includes determining whether acceleration structure traversal data of a previous ray similar to a received ray is stored in a traversal cache, and reading the stored acceleration structure traversal data, and performing image rendering based on the read acceleration structure traversal data, based on a result of the determining.