2020 IEEE International Conference on Visual Communications and Image Processing (VCIP) 2020
DOI: 10.1109/vcip49819.2020.9301804
|View full text |Cite
|
Sign up to set email alerts
|

Point Cloud Geometry Prediction Across Spatial Scale using Deep Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(15 citation statements)
references
References 9 publications
0
15
0
Order By: Relevance
“…Borges et al [5] first build lookup tables from self-similarities and then apply the obtained lookup tables to refine voxelized point clouds. Akhtar et al [6] use sparse convolutions to predict the points which are lost during the quantization process. The up-sampling results can effectively improve the quality of the decompressed point clouds.…”
Section: Post-processing Methodsmentioning
confidence: 99%
See 3 more Smart Citations
“…Borges et al [5] first build lookup tables from self-similarities and then apply the obtained lookup tables to refine voxelized point clouds. Akhtar et al [6] use sparse convolutions to predict the points which are lost during the quantization process. The up-sampling results can effectively improve the quality of the decompressed point clouds.…”
Section: Post-processing Methodsmentioning
confidence: 99%
“…However, it requires constructing a lookup table for each point cloud, which reduces the efficiency of the method. Akhtar et al [6] apply a deep neural network to predict points lost during the quantization process. The upsampled results significantly improve the quality of input point clouds.…”
Section: Refined Point Cloud Ground Truthmentioning
confidence: 99%
See 2 more Smart Citations
“…Lazzarotto and Ebrahimi (2021) perform residual coding and encode a residual between a ground-truth block and a degraded block compressed with G-PCC. (Akhtar et al, 2020) perform super-resolution using CNNs which improves the reconstruction quality significantly without any additional coding cost.…”
Section: Lossy Compressionmentioning
confidence: 99%