PF-Net: Point Fractal Network for 3D Point Cloud Completion

Huang, Zitian; Yu, Yang; Xu, Jiawen; Feng, Nan; Le, Xinyi

doi:10.1109/cvpr42600.2020.00768

Cited by 388 publications

(277 citation statements)

References 29 publications

Supporting

Mentioning

272

Contrasting

Unclassified

Order By: Relevance

“…VPC-Net [55] is designed for vehicle point cloud completion using raw LiDAR scans. PF-Net [15] uses a multi-stage strategy to generate the lost structure of the object at multiple-scale. SoftPool-Net [50] changes the max-pooling layer to a soft pooling layer, which can keep more information in multiply features.…”

Section: Template-based Approachesmentioning

confidence: 99%

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

Xia

Li³

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

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 information. Experiments are conducted on the PCN dataset and the Completion3D benchmark, demonstrating the state-of-the-art performance of the proposed ASFM-Net. Our method achieves the 1st place in the leaderboard of Completion3D and outperforms existing methods with a large margin, about 12%. The codes and trained models are released publicly at https://github.com/Yan-Xia/ASFM-Net. CCS CONCEPTS• Computing methodologies → Shape inference; Shape representations.

show abstract

Section: Template-based Approachesmentioning

confidence: 99%

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

Xia

Li³

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Since the methods we compare are applied in different datasets in their papers, to compare fairly, we follow [21] to obtain the incomplete point clouds. We train our model on eight categories of different objects in the dataset ShapeNet-Part.…”

Section: Datasetsmentioning

confidence: 99%

3D Grid Transformation Network For Point Cloud Completion

Deng

Buris

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Point cloud completion is of significant importance in 3D scene modeling because point clouds collected from sensors tend to be sparse and incomplete. Existing methods prefer to transform 2D grid points to the underlying surface of output point clouds. However, the point clouds they complete commonly retain the original plane structure and fail to recover details. To solve the problem, we propose 3D Grid Transformation Network. Unlike transforming 3D grid points to point clouds directly, we calculate their weights for the reconstructed point clouds. Our method can break the topology of the 3D grid structure and make the underlying shape of output point clouds closer to the ground truth. We validate our method on point cloud completion and experimental results show that our method can achieve better quantitative results and obtain fine-grained details.

show abstract

“…7. MLP denotes the widely used way in PointNet; CMLP is proposed in [51]. Compared with the CMLP, our IMLP adds a feature fusion step to better use high-level and low-level information.…”

Section: Ablation Studies On Aasmentioning

confidence: 99%

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

et al. 2021

View full text Add to dashboard Cite

As an essential step in the restoration of Terracotta Warriors, the results of fragments classification will directly affect the performance of fragments matching and splicing. However, most of the existing methods are based on traditional technology and have low accuracy in classification. A practical and effective classification method for fragments is an urgent need. In this case, an attention-based multi-scale neural network named AMS-Net is proposed to extract significant geometric and semantic features. AMS-Net is a hierarchical structure consisting of a multi-scale set abstraction block (MS-BLOCK) and a fully connected (FC) layer. MS-BLOCK consists of a local-global layer (LGLayer) and an improved multi-layer perceptron (IMLP). With a multi-scale strategy, LGLayer can parallel extract the local and global features from different scales. IMLP can concatenate the high-level and low-level features for classification tasks. Extensive experiments on the public data set (ModelNet40/10) and the real-world Terracotta Warrior fragments data set are conducted. The accuracy results with normal can achieve 93.52% and 96.22%, respectively. For real-world data sets, the accuracy is best among the existing methods. The robustness and effectiveness of the performance on the task of 3D point cloud classification are also investigated. It proves that the proposed end-to-end learning network is more effective and suitable for the classification of the Terracotta Warrior fragments.

show abstract

PF-Net: Point Fractal Network for 3D Point Cloud Completion

Cited by 388 publications

References 29 publications

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

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

3D Grid Transformation Network For Point Cloud Completion

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

Contact Info

Product

Resources

About