17816375. BOUNDING VOLUME HIERARCHY (BVH) WIDENING BASED ON NODE COMPRESSIBILITY simplified abstract (QUALCOMM Incorporated)
Contents
BOUNDING VOLUME HIERARCHY (BVH) WIDENING BASED ON NODE COMPRESSIBILITY
Organization Name
Inventor(s)
Adimulam Ramesh Babu of San Diego CA (US)
Srihari Babu Alla of San Diego CA (US)
Avinash Seetharamaiah of San Diego CA (US)
Jonnala Gadda Nagendra Kumar of San Diego CA (US)
David Kirk Mcallister of Holladay UT (US)
BOUNDING VOLUME HIERARCHY (BVH) WIDENING BASED ON NODE COMPRESSIBILITY - A simplified explanation of the abstract
This abstract first appeared for US patent application 17816375 titled 'BOUNDING VOLUME HIERARCHY (BVH) WIDENING BASED ON NODE COMPRESSIBILITY
Simplified Explanation
The patent application describes a system and techniques for improving the efficiency of ray tracing, a rendering technique used in computer graphics. The system involves widening a hierarchical structure used for ray tracing by determining multiple candidate hierarchical acceleration data structures and selecting the one with the best cost metric. The system also predicts the compressibility of the candidate hierarchical acceleration data structure and generates an output hierarchical acceleration data structure based on this prediction.
- The system widens a hierarchical structure for ray tracing.
- It obtains a plurality of primitives of a scene object included in a first hierarchical acceleration data structure.
- It determines one or more candidate hierarchical acceleration data structures, each including the plurality of primitives.
- It determines a cost metric for the candidate hierarchical acceleration data structures.
- It predicts the compressibility of a candidate hierarchical acceleration data structure based on the cost metric.
- It generates an output hierarchical acceleration data structure based on the compressibility prediction.
Potential applications of this technology:
- Computer graphics rendering: The improved efficiency of ray tracing can benefit various applications in computer graphics, such as video games, virtual reality, and animation production.
- Real-time rendering: The widened hierarchical structure can enhance the performance of real-time rendering systems, allowing for more complex and realistic scenes to be rendered in real-time.
- Scientific visualization: The system can be applied to scientific visualization software to improve the rendering of complex data sets, such as simulations and medical imaging.
Problems solved by this technology:
- Ray tracing efficiency: Ray tracing is a computationally intensive process, and this technology addresses the challenge of optimizing the performance of ray tracing algorithms by widening the hierarchical structure.
- Scene complexity: As scenes in computer graphics become more complex, the hierarchical acceleration data structure needs to be expanded to efficiently handle a larger number of primitives.
- Memory usage: The system aims to reduce memory usage by predicting the compressibility of the hierarchical acceleration data structure and generating a more compact output structure.
Benefits of this technology:
- Improved rendering performance: The widened hierarchical structure allows for faster ray tracing, resulting in improved rendering performance and reduced rendering times.
- Enhanced realism: By efficiently handling complex scenes, the technology enables more realistic and detailed rendering, enhancing the visual quality of computer graphics.
- Memory optimization: The compressibility prediction helps reduce memory usage, allowing for more efficient storage and processing of the hierarchical acceleration data structure.
Original Abstract Submitted
Systems and techniques are provided for widening a hierarchical structure for ray tracing. For instance, a process can include obtaining a plurality of primitives of a scene object included in a first hierarchical acceleration data structure and determining one or more candidate hierarchical acceleration data structures each including the plurality of primitives. A cost metric can be determined for the one or more candidate hierarchical acceleration data structures and, based on the cost metric, a compressibility prediction associated with a candidate hierarchical acceleration data structure of the one or more candidate hierarchical acceleration data structures can be determined. An output hierarchical acceleration data structure can be generated based on the compressibility prediction.
