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

@article{Xia2021ASFMNetAS,
  title={ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion},
  author={Yaqi Xia and Yan Xia and Wei Li and Rui Song and Kai Cao and Uwe Stilla},
  journal={Proceedings of the 29th ACM International Conference on Multimedia},
  year={2021}
}
  • Yaqi Xia, Yan Xia, Uwe Stilla
  • Published 19 April 2021
  • Computer Science
  • Proceedings of the 29th ACM International Conference on Multimedia
We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net. Specifically, the Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior. Then we design an iterative refinement unit to generate complete shapes with fine-grained details by integrating prior… 
Point cloud completion on structured feature map with feedback network
TLDR
This paper proposes 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 and integrates FSNet into a coarse-to-fine pipeline for point cloud completion.
Point cloud completion via structured feature maps using a feedback network
TLDR
This paper proposes 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, and integrates FSNet into a coarse-tofine pipeline for point cloud completion.
SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer
TLDR
A novel SeedFormer is proposed to improve the ability of detail preservation and recovery in point cloud completion by introducing a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns.
Learning Local Displacements for Point Cloud Completion
TLDR
A novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud is proposed and a second model is introduced that assembles the authors' layers within a transformer architecture, achieving state-of-the-art performance.
MFM-Net: Unpaired Shape Completion Network with Multi-stage Feature Matching
TLDR
A novel unpaired shape completion network, named MFMNet, using multi-stage feature matching, which decomposes the learning of geometric correspondence into multi-stages throughout the hierarchical generation process in the point cloud decoder.
Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis
TLDR
This work aims to conduct a comprehensive survey on various methods of point cloud completion, including point-based, convolution- based, graph-based and generative model-based approaches, etc, and summarizes the comparisons among these methods to provoke further research insights.
Temporal Point Cloud Completion With Pose Disturbance
TLDR
This work proposes a point cloud completion framework that accepts a sequence of unaligned and sparse inputs, and outputs consistent and aligned point clouds and is the first to utilize temporal information and ensure temporal consistency with limited transformation.
Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
TLDR
The insight of revealing detailed geometry is to introduce skip-transformer in SPD to learn point splitting patterns which can fit local regions the best and outperform the state-of-the-art methods under widely used benchmarks.
LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints
TLDR
LAKe-Net is proposed, a novel topology-aware point cloud completion model by localizing aligned keypoints, with a novel Keypoints-Skeleton-Shape prediction manner, and experimental results show that the method achieves the state-of-the-art performance on point cloudpletion.
A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
TLDR
This work proposes a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion that can effectively and efficiently extract multi-level features from partially observed point clouds to guide completion, and accurately manipulate spatial locations of 3D points to obtain smooth surfaces and sharp details.
...
...

References

SHOWING 1-10 OF 92 REFERENCES
Cascaded Refinement Network for Point Cloud Completion
TLDR
This work proposes a cascaded refinement network together with a coarse-to-fine strategy to synthesize the detailed object shapes and designs a patch discriminator that guarantees every local area has the same pattern with the ground truth to learn the complicated point distribution.
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
  • Yan Xia, Yusheng Xu, Uwe Stilla
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
TLDR
This work introduces a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors and proposes a novel loss function called HPHN quadruplet loss, that achieves better performance than the commonly used metric learning loss.
SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
TLDR
This paper proves that the regional activation can be incorporated in many point cloud architectures like AtlasNet and PCN, leading to better performance for geometric completion.
A Self-supervised Cascaded Refinement Network for Point Cloud Completion
TLDR
This work proposes a self-supervised object completion method, which optimizes the training procedure solely on the partial input without utilizing the fully-complete ground truth, and proposes a cascaded refinement network (CRN) with a coarse-to-fine strategy to synthesize the complete objects.
Detail Preserved Point Cloud Completion via Separated Feature Aggregation
TLDR
Qualitative and quantitative evaluations demonstrate that the proposed network outperforms current state-of-the art methods especially on detail preservation.
Variational Relational Point Completion Network
TLDR
A variational framework, Variational Relational point Completion network (VRC-Net), with two appealing properties: Probabilistic Modeling and Relational Enhancement, which shows great generalizability and robustness on real-world point cloud scans.
High Fidelity Semantic Shape Completion for Point Clouds Using Latent Optimization
TLDR
This work proposes a learning-based approach to complete incomplete 3D shapes through generative modeling and latent manifold optimization and is capable of successfully reconstructing point clouds with large missing regions with very high fidelity without having to rely on exemplar based database retrieval.
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
TLDR
A novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds, and is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid.
Point Cloud Completion by Skip-Attention Network With Hierarchical Folding
TLDR
This work proposes Skip-Attention Network (SA-Net), a skip-attention mechanism to effectively exploit the local structure details of incomplete point clouds during the inference of missing parts, and proposes a novel structure-preserving decoder with hierarchical folding for complete shape generation.
PCN: Point Completion Network
TLDR
The experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset.
...
...