Loading...
Authors
Guarda, André
Rodrigues, Nuno
Pereira, Fernando
Advisor(s)
Abstract(s)
Context and Objective: The current VM uses a dense 3D representation with dense convolutions
Problem: Heavy in computation complexity, cannot encode a full point cloud at once; Underperforms for sparse point cloud
Objective: Implement the DL models in the VM with a sparse tensor representation, and verify
its performance
Description
Keywords
JPEG PCC Core Sparse Convolutions