2021
DOI: 10.1016/j.neucom.2021.07.087
|View full text |Cite
|
Sign up to set email alerts
|

GeneCGAN: A conditional generative adversarial network based on genetic tree for point cloud reconstruction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(5 citation statements)
references
References 13 publications
0
5
0
Order By: Relevance
“…And a hybrid recovery loss function was proposed to compute the diversity between two groups of disordered data. Chen et al [84] proposed an end-toend conditional GAN called GeneCGAN. From the heredity perspective, a simulated genetic (SG) layer was devised.…”
Section: E Gan-based Methodsmentioning
confidence: 99%
“…And a hybrid recovery loss function was proposed to compute the diversity between two groups of disordered data. Chen et al [84] proposed an end-toend conditional GAN called GeneCGAN. From the heredity perspective, a simulated genetic (SG) layer was devised.…”
Section: E Gan-based Methodsmentioning
confidence: 99%
“…and KPConv [74] are further proposed to enhance industrial applications based on the point cloud, including recognition [38], [41], [62], detection [19], [91], registration [34], [39], [66], [92], sampling [5], [30], [37], generation [6], [46], and interpretation [69].…”
Section: D Data Processingmentioning
confidence: 99%
“…In convolution based method, the point cloud data is converted into voxel, whose process may cause the loss of fine-grained information [5,6]. The GAN based method uses the implicit learning of discriminator to estimate the point convergence provided by generator, whose training is time-consuming [7,8]. Since both point cloud and graph belong to non-Euclidean structure data, so we can deem each point of the input point cloud as a node and the adjacent link as edge in the graph structure.…”
Section: Introductionmentioning
confidence: 99%