← Search

Rodrigo B. Pinheiro

2 accepted papers

2024

Reducing the Complexity of Normalizing Flow Architectures for Point Cloud Attribute Compression

ICASSP 2024accepted

Existing learning-based methods to compress PCs attributes typically employ variational autoencoders (VAE) to learn compact signal representations. However, these schemes suffer from limited reconstruction quality at high bitrates due to their intrinsic lossy nature. More recently, normalizing flows…

Cited by 0SourceScholar
2023

NF-PCAC: Normalizing Flow Based Point Cloud Attribute Compression

ICASSP 2023accepted

Learning-based point cloud (PC) compression is a promising research avenue to reduce the transmission and storage costs for PC applications. Existing learning-based methods to compress PCs have mainly focused on geometry and employ variational autoencoders to learn compact signal representations. Ho…

Cited by 0SourceScholar