Lossless Coding of Point Cloud Geometry using a Deep Generative Model

Autor: Dat Thanh Nguyen, Giuseppe Valenzise, Pierre Duhamel, Maurice Quach
Přispěvatelé: Laboratoire des signaux et systèmes (L2S), CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)
Jazyk: angličtina
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Point cloud
Computer Science - Computer Vision and Pattern Recognition
Point Cloud Coding
02 engineering and technology
Machine Learning (cs.LG)
Octree
Deep Learning
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing
0202 electrical engineering
electronic engineering
information engineering

Media Technology
FOS: Electrical engineering
electronic engineering
information engineering

Electrical and Electronic Engineering
Block (data storage)
Lossless compression
Context model
context model
Image and Video Processing (eess.IV)
Electrical Engineering and Systems Science - Image and Video Processing
G-PCC
Arithmetic coding
arithmetic coding
Generative model
Probability distribution
020201 artificial intelligence & image processing
Algorithm
Zdroj: IEEE Transactions on Circuits and Systems for Video Technology
IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2021, 31 (12), pp.4617-4629. ⟨10.1109/TCSVT.2021.3100279⟩
ISSN: 1051-8215
DOI: 10.1109/TCSVT.2021.3100279⟩
Popis: This paper proposes a lossless point cloud (PC) geometry compression method that uses neural networks to estimate the probability distribution of voxel occupancy. First, to take into account the PC sparsity, our method adaptively partitions a point cloud into multiple voxel block sizes. This partitioning is signalled via an octree. Second, we employ a deep auto-regressive generative model to estimate the occupancy probability of each voxel given the previously encoded ones. We then employ the estimated probabilities to code efficiently a block using a context-based arithmetic coder. Our context has variable size and can expand beyond the current block to learn more accurate probabilities. We also consider using data augmentation techniques to increase the generalization capability of the learned probability models, in particular in the presence of noise and lower-density point clouds. Experimental evaluation, performed on a variety of point clouds from four different datasets and with diverse characteristics, demonstrates that our method reduces significantly (by up to 30%) the rate for lossless coding compared to the state-of-the-art MPEG codec.
This paper has been submitted to the IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). arXiv admin note: text overlap with arXiv:2011.14700
Databáze: OpenAIRE