Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation

Abstract

Most existing point cloud completion methods are only applicable to partial point clouds without any noises and outliers, which does not always hold in practice. We propose in this paper an end-toend network, named CS-Net, to complete the point clouds contaminated by noises or containing outliers. In our CS-Net, the completion and segmentation modules work collaboratively to promote each other, benefited from our specifically designed cascaded structure. With the help of segmentation, more clean point cloud is fed into the completion module. We design a novel completion decoder which harnesses the labels obtained by segmentation together with FPS to purify the point cloud and leverages KNN-grouping for better generation. The completion and segmentation modules work alternately share the useful information from each other to gradually improve the quality of prediction. To train our network, we build a dataset to simulate the real case where incomplete point clouds contain outliers. Our comprehensive experiments and comparisons against state-of-the-art completion methods demonstrate our superiority. We also compare with the scheme of segmentation followed by completion and their end-to-end fusion, which also proves our efficacy.

Point Cloud Completion: A Survey

“…PDCNet [156] uses density-based clustering algorithms to reduce noise. Ma et al [114] uses a segmentation task to define the boundary of the object and its parts. Any point outside the boundary can be removed by Farthest Point Sampling (FPS) and thus a cleaner output is made.…”

“…Tsai et al [190] use completion to neutralize scan pattern discrepancy in traffic-scene lidar scans between different datasets that cause detection algorithms to overfit on the data they are trained on. Segmentation tasks [191] [100] can benefit from shape priors learned from completion networks and vice versa [51], [114].…”

“…Evaluation metrics that can measure the effect of noise and density distribution could be useful to analyse the completion results with respect to the inputs. Assistive Tasks and Feature Representation: During our survey, we found a few works that take assistance from other point clouds tasks such as segmentation [51], [98], [114], generation [167], upsampling [150], [208], classification [72], and object detection [7], [209]. Completion also benefits from the use of multitask point generation models [143], [145] and multitask feature learning [210].…”