Introduction to immersive video technologies

Valenzise, Giuseppe; Zerman, Emin; Alain, Martin; Özçinar, Çağrı

doi:10.1016/b978-0-32-391755-1.00007-9

Cited by 3 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Content consumption has been evolving towards immersive formats [1], specially for entertainment. In this context, Point Clouds (PCs) are one of the most popular volumetric representations.…”

Section: Introductionmentioning

confidence: 99%

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

Pinheiro,

Marvie,

Valenzise

et al. 2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

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 (NF) have been proposed as an alternative solution. NFs are invertible networks that can achieve lossless reconstruction, at the cost of very large architectures with high memory and computational footprint. This paper proposes an improved NF architecture with reduced complexity called RNF-PCAC. It is composed of two operating modes specialized for low and high bitrates, combined in a rate-distortion optimized fashion. Our approach reduces the number of parameters of the existing NF architectures by over 6×. At the same time, it achieves state-of-the-art coding gains compared to previous learning-based methods and, for some PCs, it matches the performance of G-PCC (v.21).

show abstract

Section: Introductionmentioning

confidence: 99%

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

Pinheiro,

Marvie,

Valenzise

et al. 2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…In the past few years, video content consumption has been evolving towards immersive formats [1], in particular for entertainment. For example, the most recent Olympic Games in Tokyo (2021) featured a 3D replay that brought the spectator closer to the action.…”

Section: Introductionmentioning

confidence: 99%

NF-PCAC: Normalizing Flow Based Point Cloud Attribute Compression

Pinheiro

Marvie

Valenzise

et al. 2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

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. However, autoencoders leverage low-dimensional bottlenecks that limit the maximum reconstruction quality, even at high bitrates. In this paper, we propose a different and novel approach to compress PC attributes by using normalizing flows. Since normalizing flows model invertible transforms, the proposed approach can achieve better reconstruction quality than variational autoencoders over a large range of bitrates. Our Normalizing Flow-based Point Cloud Attribute Compression (NF-PCAC) outperforms previous learning-based methods for attribute compression, and has comparable performance as G-PCC v.14, showing the potential of this scheme for PC compression.

show abstract