Presentation
Fused Sampling and Grouping with Search Space Reduction for Efficient Point Cloud Acceleration
DescriptionPoint-based deep neural networks have demonstrated remarkable ability in analyzing point cloud. However, challenges arise in sampling and grouping layers, particularly in terms of time and energy consumption. In this paper, we introduce a Morton code-based data structure which stores point data with the shared upper bits together. We also propose a fused sampling and grouping approach with a reduced search space, which reuses the point data and the calculated distances. Additionally, a dedicated hardware supporting the proposed method is introduced. Experimental results show that our approach effectively reduces the number of calculations and data accesses with negligible accuracy loss.
Event Type
Research Manuscript
TimeThursday, June 2711:00am - 11:15am PDT
Location3010, 3rd Floor
AI
Design
AI/ML Architecture Design