ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

Xia, Yaqi; Xia, Yan; Wei, Li; Song, Rui; Cao, Kailang; Stilla, Uwe

doi:10.48550/arxiv.2104.09587

Cited by 11 publications

(10 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significantly, they adopt an up-sampling approach to generate a more uniform point cloud. Furthermore, they devised ASFM-Net [35], in which the asymmetrical Siamese auto-encoder (AE) generates a coarse but complete output and the following refinement unit aims to recover a final point cloud with fine-grained details. Mendoza et al [36] proposed a network with an end-to-end pattern consisting of two neural networks: the missing part prediction network and the merging-refinement network.…”

Section: A Point-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Fei¹,

Yang²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field.

show abstract

Section: A Point-based Methodsmentioning

confidence: 99%

“…ASFM-Net [35] ASFM-Net is an asymmetrical Siamese auto-encoder model to learn a shape prior information.…”

Section: Highlights Limitationmentioning

confidence: 99%

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Fei¹,

Yang²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…PF-Net [11], DeCo [1], and PoinTr [46] only generate the missing part of the object to preserve the spatial arrangements of the original part. VRCNet [21] and ASFM-Net [39] improve the global features by narrow the distribution difference between the incomplete and complete point cloud. CRN [32] and SnowflakeNet [40] generate the complete point cloud following in a progressive manner.…”

Section: Related Workmentioning

confidence: 99%

Point cloud completion on structured feature map with feedback network

Zejia¹,

Huang²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structures as well as surface details given a partial input, a fundamental component is a good feature representation that can capture both global structure and local geometric details. Towards this end, we first propose FSNet, a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local regions. We then integrate FSNet into a coarse-to-fine pipeline for point cloud completion. Specifically, a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud. Next, a point cloud upsampling network is used to generate dense point cloud from the partial input and the coarse intermediate output. To efficiently exploit the local structures and enhance the point distribution uniformity, we propose IFNet, a point upsampling module with self-correction mechanism that can progressively refine details of the generated dense point cloud.We conduct both qualitative and quantitative experiments on ShapeNet, MVP, and KITTI datasets, which demonstrate that our method outperforms state-of-the-art point cloud completion approaches.

show abstract

“…They then fix and reuse the decoder to train a new encoder on incomplete shapes where alignment of the predicted result with the incomplete input shape is respected by applying a maximum likelihood (ML) loss. ASFM-Net [31] maps the partial and complete input point clouds into a common latent space to capture detailed shape priors and better respect the input.…”

Section: Shape Completionmentioning

confidence: 99%

Multimodal Shape Completion via IMLE

Arora,

Mishra,

Peng

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

Cited by 11 publications

References 66 publications

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Point cloud completion on structured feature map with feedback network

Multimodal Shape Completion via IMLE

Contact Info

Product

Resources

About