Point Cloud Completion by Skip-Attention Network With Hierarchical Folding

Wen, Xin; Li, Tianyang; Han, Zhizhong; Liu, Yu‐Shen

doi:10.1109/cvpr42600.2020.00201

Cited by 262 publications

(166 citation statements)

References 34 publications

Supporting

Mentioning

164

Contrasting

Unclassified

Order By: Relevance

“…This idea is inspired by point cloud completion [14]. In contrast to [14], the output produced by 3D-CN has the following properties: (1) it represents the same complete geometric shape (a complete body shape in the example of Figure 1), ( 2) it has the same number U of points for any input partial point cloud and ( 3) it has the same order of points, irrespective of the input. Based on these properties, one-to-one correspondences between partial point clouds of the same object are naturally built.…”

Section: Problem Statementmentioning

confidence: 99%

“…Ablation study: Based on the 400 testing data which is not included in the training, in this section we try to explore the effects on the registration of sparse and dense correspondences. We also compare our correspondences with the complete point clouds (CPC) from point completion networks [14]. Due to lacking the one-to-one correspondences for complete point clouds, point-to-point ICP is applied to compute the transformation.…”

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Method for registration of 3D shapes without overlap for known 3D priors

Munteanu

2021

Electronics Letters

View full text Add to dashboard Cite

In 3D registration of point clouds, the goal is to find an optimal transformation that aligns the input shapes, provided that they have some overlap. Existing methods suffer from performance degradation when the overlapping ratio between the neighbouring point clouds is small. So far, there is no existing method that can be adopted for aligning shapes with no overlap. In this letter, to the best of knowledge, the first method for the registration of 3D shapes without overlap, assuming that the shapes correspond to partial views of a known semi-rigid 3D prior is presented. The method is validated and compared to existing methods on FAUST, which is a known dataset used for human body reconstruction. Experimental results show that this approach can effectively align shapes without overlap. Compared to existing state-of-theart methods, this approach avoids iterative optimization and is robust to outliers and inherent inaccuracies induced by an initial rough alignment of the shapes. Introduction: 3D registration is a classical and fundamental problem for countless applications. Since commodity depth cameras become less expensive and more accurate, depth images play an increasingly important role in numerous tasks [1]. In order to obtain comprehensive information from 3D scenery, point clouds captured from multiple views need to be aligned. The well-established method is iterative closest point (ICP) [2] based on which a myriad of flavours have been proposed. In ICP, given a source shape and a target shape, the following steps are performed: (1) for each point in the source shape, identify the closest corresponding point in the target shape; (2) predict the transformation by minimizing the mean square Euclidean distance between these correspondences; (3) transform the source shape using the predicted transformation from step 2; (4) iterate the above steps until the mean square distance reaches a pre-defined threshold. ICP and its variants are the dominating methods for the task of 3D registration. However, ICP-based methods assume that the source and target shapes have been roughly aligned with a sufficient overlap.. Deep learning has shown its excellent ability to solve various problems which are difficult or impossible to address using traditional approaches. Recent research strives to explore 3D registration via deep learning [3], [4], [5], [6]. However, these methods are designed for shapes that partially overlap. In this letter, we present a novel deep learning method for 3D shape registration. Compared to the existing methods, the main advantage of our method is that we successfully handled the non-overlapping shape registration problem. We assume that the shapes correspond to partial views of a known semi-rigid 3D prior. This problem is impossible to be addressed using ICP due to the lack of point correspondences. This is addressed in this letter of which the main contributions can be summarized as follows:

show abstract

Section: Problem Statementmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

Method for registration of 3D shapes without overlap for known 3D priors

Munteanu

2021

Electronics Letters

View full text Add to dashboard Cite

show abstract

“…SoftPool-Net [50] changes the max-pooling layer to a soft pooling layer, which can keep more information in multiply features. SA-Net [51] adopts a self-attention mechanism [54]to effectively exploit the local structure details. Zhang et al [62] propose a feature aggregation strategy to preserve the primitive details.…”

Section: Template-based Approachesmentioning

confidence: 99%

“…Compared to using the max-pooling operation to extract global features, SoftPoolNet [50] proposes a soft pooling approach, which selects multiple high-scoring activation. To preserve local structures, SA-Net [51] uses a skip-attention mechanism to transfer local features to the decoder. However, they all rely on the global feature extracted from the partial inputs to generate complete point clouds.…”

Section: Introductionmentioning

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

“…In the 3D domain, interactive semantic segmentation relies on user strokes to propagate segmentation [ 21 , 22 ]. For 3D segmentation, Xin Wen et al [ 23 ] proposed new attention mechanism to predict the semantic labels. PointNet [ 1 ] and subsequent work [ 24 , 25 ] use multi-layer perceptron (MLP) to generate fine-grained point-level segmentation.…”

Section: Related Workmentioning

confidence: 99%

Semantic Point Cloud Segmentation Using Fast Deep Neural Network and DCRF

Rao

Zhang

Cheng

et al. 2021

Sensors

View full text Add to dashboard Cite

Accurate segmentation of entity categories is the critical step for 3D scene understanding. This paper presents a fast deep neural network model with Dense Conditional Random Field (DCRF) as a post-processing method, which can perform accurate semantic segmentation for 3D point cloud scene. On this basis, a compact but flexible framework is introduced for performing segmentation to the semantics of point clouds concurrently, contribute to more precise segmentation. Moreover, based on semantics labels, a novel DCRF model is elaborated to refine the result of segmentation. Besides, without any sacrifice to accuracy, we apply optimization to the original data of the point cloud, allowing the network to handle fewer data. In the experiment, our proposed method is conducted comprehensively through four evaluation indicators, proving the superiority of our method.

show abstract

Point Cloud Completion by Skip-Attention Network With Hierarchical Folding

Cited by 262 publications

References 34 publications

Method for registration of 3D shapes without overlap for known 3D priors

Method for registration of 3D shapes without overlap for known 3D priors

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

Semantic Point Cloud Segmentation Using Fast Deep Neural Network and DCRF

Contact Info

Product

Resources

About