RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2<sup>D</sup>-Tree Representation

Ali, Sk Aziz; Kahraman, Kerem; Reis, Gerd; Stricker, Didier

doi:10.1109/cvpr46437.2021.01290

Cited by 14 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GMM parameters are calculated using differentiable computing module and the optimal transformation is recovered. Different from the way of voxelizing point cloud, Ali et al (2021) proposed RPSRNet, which used the tree representation based on Barnes Hut (BH) (Barnes and Hut, 1986) for the input point cloud data. First, the model recursively subdivides the normalized boundary space of the input point cloud to the limit depth to construct the BH tree.…”

Section: End-to-endmentioning

confidence: 99%

A review of rigid point cloud registration based on deep learning

Chen,

Feng,

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

With the development of 3D scanning devices, point cloud registration is gradually being applied in various fields. Traditional point cloud registration methods face challenges in noise, low overlap, uneven density, and large data scale, which limits the further application of point cloud registration in actual scenes. With the above deficiency, point cloud registration methods based on deep learning technology gradually emerged. This review summarizes the point cloud registration technology based on deep learning. Firstly, point cloud registration based on deep learning can be categorized into two types: complete overlap point cloud registration and partially overlapping point cloud registration. And the characteristics of the two kinds of methods are classified and summarized in detail. The characteristics of the partially overlapping point cloud registration method are introduced and compared with the completely overlapping method to provide further research insight. Secondly, the review delves into network performance improvement summarizes how to accelerate the point cloud registration method of deep learning from the hardware and software. Then, this review discusses point cloud registration applications in various domains. Finally, this review summarizes and outlooks the current challenges and future research directions of deep learning-based point cloud registration.

show abstract

Section: End-to-endmentioning

confidence: 99%

A review of rigid point cloud registration based on deep learning

Chen,

Feng,

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Supervised learning methods for 3D shape processing require an efficient input data representation. Apart from common learning representations of 3D shapes -such as regular voxel grids [24,49], point clouds [32], Oc-trees [44], Barnes-Hut 2 D -tree [5], depth-maps [27], and meshes [16], the popularity of implicit representation [28,48,29] has recently increased. These representations [48,29] serve as a continuous representation on the volumetric occupancy grid [28] to encode the iso-surface of a shape.…”

Section: Related Workmentioning

confidence: 99%

BCom-Net: Coarse-to-Fine 3D Textured Body Shape Completion Network

Karadeniz¹,

Ali²,

Kacem³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Reconstructing 3D human body shapes from 3D partial textured scans remains a fundamental task for many computer vision and graphics applications -e.g., body animation, and virtual dressing. We propose a new neural network architecture for 3D body shape and highresolution texture completion -TSCom-Net -that can reconstruct the full geometry from mid-level to high-level partial input scans. We decompose the overall reconstruction task into two stages -first, a joint implicit learning network (SCom-Net and TCom-Net) that takes a voxelized scan and its occupancy grid as input to reconstruct the full body shape and predict vertex textures. Second, a high-resolution texture completion network, that utilizes the predicted coarse vertex textures to inpaint the missing parts of the partial 'texture atlas'. A Thorough experimental evaluation on 3DBodyTex.V2 dataset shows that our method achieves competitive results with respect to the state-of-the-art while generalizing to different types and levels of partial shapes. The proposed method has also ranked second in the track1 of SHApe Recovery from Partial textured 3D scans (SHARP [37,2]) 2022 1 challenge1.

show abstract

“…In recent years, owing to the discriminative representation ability of deep learning, deep point cloud registration methods have achieved increasing research interests. Most of these methods (Pais et al 2020;Fu et al 2021;Ali et al 2021) focus on learning the rigid transformation in a supervised manner, where a large number of ground truth transformations are required as the supervision signal for model training. However, collecting required ground truth transformations is expensive and time-consuming, which may greatly increase the training cost and hinder their applications in the real world.…”

Section: Introductionmentioning

confidence: 99%

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Shen

Hui

Jiang

et al. 2022

AAAI

View full text Add to dashboard Cite

Unsupervised point cloud registration algorithm usually suffers from the unsatisfied registration precision in the partially overlapping problem due to the lack of effective inlier evaluation. In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration. It is expected to capture the discriminative geometric difference between the source neighborhood and the corresponding pseudo target neighborhood for effective inlier distinction. Specifically, our model consists of a matching map refinement module and an inlier evaluation module. In our matching map refinement module, we improve the point-wise matching map estimation by integrating the matching scores of neighbors into it. The aggregated neighborhood information potentially facilitates the discriminative map construction so that high-quality correspondences can be provided for generating the pseudo target point cloud. Based on the observation that the outlier has the significant structure-wise difference between its source neighborhood and corresponding pseudo target neighborhood while this difference for inlier is small, the inlier evaluation module exploits this difference to score the inlier confidence for each estimated correspondence. In particular, we construct an effective graph representation for capturing this geometric difference between the neighborhoods. Finally, with the learned correspondences and the corresponding inlier confidence, we use the weighted SVD algorithm for transformation estimation.Under the unsupervised setting, we exploit the Huber function based global alignment loss, the local neighborhood consensus loss and spatial consistency loss for model optimization. The experimental results on extensive datasets demonstrate that our unsupervised point cloud registration method can yield comparable performance.

show abstract

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2^D-Tree Representation

Cited by 14 publications

References 52 publications

A review of rigid point cloud registration based on deep learning

A review of rigid point cloud registration based on deep learning

BCom-Net: Coarse-to-Fine 3D Textured Body Shape Completion Network

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Contact Info

Product

Resources

About

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation

Cited by 14 publications

References 52 publications

A review of rigid point cloud registration based on deep learning

A review of rigid point cloud registration based on deep learning

BCom-Net: Coarse-to-Fine 3D Textured Body Shape Completion Network

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Contact Info

Product

Resources

About

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2^D-Tree Representation