Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks – trained on synthetic data – struggle with real-world degradations. In this work, we tackle the problem of completing and denoising highly corrupted partial point clouds affected by multiple simultaneous degradations. To benchmark robustness, we introduce the Corrupted Point Cloud Completion Dataset (CPCCD), which highlights the limitations of current methods under diverse corruptions. Building on these insights, we propose DWCNet (Denoising-While-Completing Network), a completion framework enhanced with a Noise Management Module (NMM) that leverages contrastive learning and self-attention to suppress noise and model structural relationships. DWCNet achieves state-of-the-art performance on both clean and corrupted, synthetic and real-world datasets. The dataset and code will be publicly available at https://github.com/keneniwt/DWCNET-Robust-Point-Cloud-Completion-against-Corruptions .

Point cloud completion is the task of producing a complete 3D shape given an input of a partial point cloud. It has become a vital process in 3D computer graphics, vision and applications such as autonomous driving, robotics, and augmented reality. These applications often rely on the presence of a complete 3D representation of the environment. Over the past few years, many completion algorithms have been proposed and a substantial amount of research has been carried out. However, there are not many in-depth surveys that summarise the research progress in such a way that allows users to make an informed choice of what algorithms to employ given the type of data they have, the end result they want, the challenges they may face and the possible strategies they could use. In this study, we present a comprehensive survey and classification of articles on point cloud completion untill August 2023 based on the strategies, techniques, inputs, outputs, and network architectures. We will also cover datasets, evaluation methods, and application areas in point cloud completion. Finally, we discuss challenges faced by the research community and future research directions.

Three-dimensional (3-D) data is regularly used to create 3-D images that are rendered onto a plane and shown on a two-dimensional (2-D) display. Stereoscopic displays are becoming more widespread and are currently available at consumer level prices. With these displays it is possible to see images with a high-quality perception of depth and with a greater sense of realism. It is an exciting time in the 3-D displays market as the current generation of 3-D display technologies continues to develop. A number of technologies for 3-D displays have existed for some time, many of which are based on liquid crystal displays (LCDs). LCDs combined with the parallax barrier method have a number of advantages in terms of cost, ease of manufacture, size, weight,and most importantly the ability to switch from 2-D to 3-D mode. Several consumer products are available based on this type of display. Applications such as entertainment, scientific visualization, advertising, and education benefit greatly from the improved realism offered by stereoscopic displays. There are many challenges to creating suitable images for 3-D displays; some have been solved and others are receiving attention. In order to build the 3-D display market, industry will need to tackle all of them in order to support the content creators and provide the features and ease of use that end users require. The aim of this paper is to describe and compare the core 3-D display technologies, bring together a number of important considerations for content creation and discuss some of the applications that have a strong benefit from using 3-D images on a 3-D display.