ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer

by   Shanshan Li, et al.

Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies. Then, in order to better perceive the position of missing points, we design a missing part sensitive transformer, which converts random normal distribution into reasonable position information, and uses proxy alignment to refine the missing proxies. It makes the predicted point proxies more sensitive to the features and positions of the missing part, and thus make these proxies more suitable for subsequent coarse-to-fine processes. Experimental results show that our method outperforms state-of-the-art completion networks on several benchmark datasets and has the fastest inference speed. Code is available at


page 3

page 6

page 12

page 17

page 18


Refinement of Predicted Missing Parts Enhance Point Cloud Completion

Point cloud completion is the task of predicting complete geometry from ...

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

Point cloud completion has become increasingly popular among generation ...

PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

Point clouds captured in real-world applications are often incomplete du...

Point Cloud Completion by Learning Shape Priors

In view of the difficulty in reconstructing object details in point clou...

Completing point cloud from few points by Wasserstein GAN and Transformers

In many vision and robotics applications, it is common that the captured...

SRPCN: Structure Retrieval based Point Completion Network

Given partial objects and some complete ones as references, point cloud ...

Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians

Generating dense point clouds from sparse raw data benefits downstream 3...

Please sign up or login with your details

Forgot password? Click here to reset