Guarda, AndréRodrigues, NunoPereira, Fernando2023-07-272023-07-272023-07http://hdl.handle.net/10400.8/8701Context 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 performanceengJPEG PCC CoreSparse Convolutionsother2023-07-27cv-prod-3311450