Latent Space Slicing for Enhanced Entropy Modeling In Learning-Based Point Cloud Geometry Compression

The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research community and standardisation groups such as JP...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 4878 - 4882
Hlavní autori: Frank, Nicolas, Lazzarotto, Davi, Ebrahimi, Touradj
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 23.05.2022
Predmet:
compression
deep learning
entropy modeling
Octrees
Point cloud
Point cloud compression
Redundancy
Three-dimensional displays
Thresholding (Imaging)
Training
Transform coding
ISSN:2379-190X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research community and standardisation groups such as JPEG and MPEG. Learned autoencoder architectures based on 3D convolutional layers are popular solutions and have demonstrated higher performance when adopting latent space entropy modeling based on learned hyperpriors. We propose an enhanced entropy model that takes into account both the hyperprior and previously encoded latent features to estimate the mean and scale of compressed features. The obtained results show a large increase in performance, with a BD PSNR gain of 5.75dB when compared to the Octree coding module in G-PCC for the D2 PSNR metric. We also perform an ablation study to quantify the impact of network parameters in the performance of the model, drawing useful insights for future research.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747496