PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

Deng, Haowen; Birdal, Tolga; Ilić, Slobodan

doi:10.1109/cvpr.2018.00028

Cited by 503 publications

(428 citation statements)

References 43 publications

Supporting

Mentioning

426

Contrasting

Order By: Relevance

“…We observe that our extracted local geometric descriptors outperform the other learning‐based methods and hand‐crafted methods, which include the learned‐based descriptors of 3DMatch [ZSN*17], LMVCNN method [HKC*18] and some hand‐crafted local descriptors (PCA descriptor, Spin Images, Shape Contexts and SDF features) commonly used in the 3D shape analysis. Specially, we compare our method with PPFNet [DBI18], which is similar with our method, but they use pointnet as the based network to extract the local features and then concatenate them with the global features. The CMC cure shows that our method can obtain better results.…”

Section: Methodsmentioning

confidence: 99%

“…Inspired by the PointNet architecture, some methods directly learn the point descriptors from local point patches. PPFNet [DBI18] applies a group of PointNets to extract the features of the local point cloud and use a max‐pooling layer to aggregates all the local features into a global one, summarizing the distinct local information to the global context of the local patches. PCPNet [GKOM18] is also based on the PointNet and changes the first transformation to learn the local properties (normals and curvatures) of 3D shapes.…”

Section: Related Workmentioning

confidence: 99%

“…Both streams share the same architecture and underlying weights. We use the N‐tuple L 2 norm as a similarity metric between point descriptors, modelled during training with the N‐tuple contrastive loss function [DBI18]. This loss minimizes the L 2 distance between descriptors of corresponding 3D point pairs (matches), while pulling apart the L 2 distance between descriptors of non‐corresponding 3D point pairs.…”

Section: Algorithmmentioning

confidence: 99%

“…Actually, the descriptors in large deformation parts also have point correspondences. Although the PPFNet [DBI18] learns the point descriptors by introducing a max‐pooling layer to aggregate all the local features into a global one, summarizing the distinctly local information to the global context, the max‐pooling layer do not consider the shape deformation and hierarchical structure, which aggregates the different level features to global shape context. Then Huang et al .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Jian-hui

Wang

Mao

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

We present a novel deep learning approach to extract point‐wise descriptors directly on 3D shapes by introducing Siamese Point Networks, which contain a global shape constraint module and a feature transformation operator. Such geometric descriptor can be used in a variety of shape analysis problems such as 3D shape dense correspondence, key point matching and shape‐to‐scan matching. The descriptor is produced by a hierarchical encoder–decoder architecture that is trained to map geometrically and semantically similar points close to one another in descriptor space. Benefiting from the additional shape contrastive constraint and the hierarchical local operator, the learned descriptor is highly aware of both the global context and local context. In addition, a feature transformation operation is introduced in the end of our networks to transform the point features to a compact descriptor space. The feature transformation can make the descriptors extracted by our networks unaffected by geometric differences in shapes. Finally, an N‐tuple loss is used to train all the point descriptors on a complete 3D shape simultaneously to obtain point‐wise descriptors. The proposed Siamese Point Networks are robust to many types of perturbations such as the Gaussian noise and partial scan. In addition, we demonstrate that our approach improves state‐of‐the‐art results on the BHCP benchmark.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Jian-hui

Wang

Mao

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Another work inspired by the PointNet was introduced by Deng et al . recently [DBI18]. They discussed limitations of the PointNet such as constructing task‐specific local descriptors.…”

Section: Data‐driven 3d Shape Descriptorsmentioning

confidence: 99%

A Survey on Data‐Driven 3D Shape Descriptors

Rostami

Bashiri

Rostami

et al. 2018

Computer Graphics Forum

View full text Add to dashboard Cite

Recent advances in scanning device technologies and improvements in techniques that generate and synthesize 3D shapes have made 3D models widespread in various fields including medical research, biology, engineering, etc. 3D shape descriptors play a fundamental role in many 3D shape analysis tasks such as point matching, establishing point‐to‐point correspondence, shape segmentation and labelling, and shape retrieval to name a few. Various methods have been proposed to calculate succinct and informative descriptors for 3D models. Emerging data‐driven techniques use machine learning algorithms to construct accurate and reliable shape descriptors. This survey provides a thorough review of the data‐driven 3D shape descriptors from the machine learning point of view and compares them in different criteria. Also, a comprehensive taxonomy of the existing descriptors is proposed based on the exploited machine learning algorithms. Advantages and disadvantages of each category have been discussed in detail. Besides, two alternative categorizations from the data type and the application perspectives are presented. Finally, some directions for possible future research are also suggested.

show abstract

Multi‐scale point cloud registration based on topological structure

Dong

Zhao

Zhang

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

The establishment of point‐to‐point correspondence between point clouds is called three‐dimensional point matching, which is widely used in computer vision, computer graphics, robotics and other fields. When the scale of source point cloud and target point cloud are different, it brings great difficulties to obtain the satisfactory matching result. Therefore, the article proposes a registration algorithm to solve this problem effectively. First, we construct a multi‐scale space related to Gaussian standard deviation. Second, we use a topological similarity of two directed trees constructed by feature points coming from two point clouds for fuzzy matching. Finally, we use local matching and global matching methods to find the corresponding relationship between patches in multi‐scale space. We find the feature correspondence of different scales in multi‐scale space and get the scale factor. Our method improves the accuracy of matching by eliminating mismatch caused by descriptor matching and local geometry matching. We show great performance of our approach by conducting extensive experiments, which outperforms other state‐of‐the‐art methods, in particular, it provides a valuable tool for point cloud registration.

show abstract

PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

Cited by 503 publications

References 43 publications

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

A Survey on Data‐Driven 3D Shape Descriptors

Multi‐scale point cloud registration based on topological structure

Contact Info

Product

Resources

About