Early Depth Testing for Hidden Surface Removal

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current graphics processing systems face inefficiencies due to 'overdraw' issues, where primitives are processed sequentially and not in perfect front-to-back order, leading to redundant rendering operations and increased memory bandwidth requirements, which existing techniques like early occlusion culling and per-sample sorting struggle to fully address without significant costs or practical limitations.

Innovation Solution

The proposed method involves performing early depth tests on larger patches of the render output, determining the number and distribution of depth value regions within these patches, and using this information to selectively perform depth tests, allowing for more precise and efficient removal of hidden surfaces without the need for costly per-sample or per-fragment sorting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If primitives are processed sequentially in current graphics processing systems, then the processing order is simple to implement, but overdraw occurs leading to redundant rendering operations and increased memory bandwidth requirements

Engineering Contradiction:
Improvesimplicity of processing order implementationVSAvoidrendering efficiency
Core Design Contradiction:
Ease of manufactureVSProductivity

Solution Approach 1:

The patent performs early depth testing before the main rendering process to identify and eliminate hidden surfaces in advance. By testing depth values of fragments against the depth buffer early in the pipeline, the system determines which fragments are visible before committing full rendering resources, thereby preventing overdraw and redundant processing of hidden primitives.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If early occlusion culling is used to remove hidden surfaces, then redundant rendering is reduced, but the technique cannot fully address the problem without significant costs or practical limitations

Engineering Contradiction:
Improvereduction of redundant renderingVSAvoidcomplexity of hidden surface removal technique
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the rendering process into distinct stages: early depth testing, fragment generation, and main rendering. By separating the depth test operation from the main rendering pipeline and performing it early on generated fragments, the system achieves efficient hidden surface removal without requiring complex per-sample sorting or other sophisticated techniques.

Inventive Principle:
Principle #1Segmentation

3Productivity

If per-sample sorting is performed to achieve perfect front-to-back order, then overdraw is eliminated, but the processing cost and complexity increase significantly

Engineering Contradiction:
Improveelimination of overdrawVSAvoidcomplexity of sorting operation
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent extracts the depth testing operation from the main rendering pipeline and performs it independently on fragments early in the process. By taking out the depth comparison function and applying it to fragments before they enter the full rendering pipeline, the system achieves efficient hidden surface removal without requiring expensive per-sample sorting operations.

Inventive Principle:
Principle #2Taking out (Extraction)

4Measurement precision

If depth tests are performed on individual sampling points, then precision is maintained, but processing time increases due to the large number of tests required

Engineering Contradiction:
Improvedepth test precisionVSAvoidprocessing time for depth tests
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent merges multiple fragment depth tests into a unified early depth testing stage that processes fragments in batches. By combining the depth testing operation with fragment generation and performing tests on multiple fragments simultaneously rather than individually at later stages, the system maintains precision while reducing total processing time.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS9558585B2Hidden surface removal in graphics processing systems
Publication Date: 2017.01.31 ARM LTD
  • US9558585B2 patent drawing
  • US9558585B2 patent drawing
  • US9558585B2 patent drawing

AI summary

A graphics processing pipeline 1 includes a rasteriser 3 that tests patches representing respective different regions of a render output against the edges of primitives 2 to determine if the primitive at least partially covers the patch and an early depth test stage 4 that performs early depth tests for primitives in respect of patches of the render output that the primitive has been found by the rasteriser at least partially to cover, by using depth test information 5 associated with a patch indicating the number and distribution of different depth value regions associated with the patch to determine the depth value region or regions associated with the patch that the primitive should be depth tested against, and then performing a depth test or tests for the primitive in respect of the respective determined depth value region or regions associated with the patch.