Classification of objects from 3-D point clouds has become an increasingly relevant task across many computer-vision applications. However, few studies have investigated explainable methods. In this article, a new prototype-based and classification method called eXplainable cloud classifier (XPCC) is proposed. The XPCC offers several advantages over previous nonexplainable First, the uses local...

Point clouds collected by real-world sensors are always unaligned and sparse, which makes it hard to reconstruct the complete shape of object from a single frame data. In this work, we manage provide point sparse input with pose disturbance limited translation rotation. We also use temporal information enhance completion model, refining output sequence inputs. With help gated recovery units(GRU...

In this paper, we introduce a non-rigid registration pipeline for pairs of unorganized point clouds that may be topologically different. Standard warp field estimation algorithms, even under robust, discontinuity-preserving regularization, tend to produce erratic motion estimates on boundaries associated with `close-to-open' topology changes. We overcome limitation by exploiting backward motion...

Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotation-invariant feature descriptors or learning canonical spaces where objects are semantically aligned. Examinations of frameworks seldom looked into. In this work, we review (RI) in terms cloud registration (PCR) and propose an effective framework via three sequential stages, namely shape encodin...

For a long time, the point cloud completion task has been regarded as pure generation task. After obtaining global shape code through encoder, complete is generated using priorly learnt by networks. However, such models are undesirably biased towards prior average objects and inherently limited to fit geometry details. In this letter, we propose Graph-Guided Deformation Network, which respectiv...

Point cloud registration is a core task in 3D perception, which aims to align two point clouds. Moreover, the of clouds with low overlap represents harder challenge, where previous methods tend fail. Recent deep learning-based approaches attempt overcome this issue by learning find overlapping regions whole scene. However, they still lack robustness and accuracy, thus might not be suitable for ...

Photo-realistic point cloud capture and transmission are the fundamental enablers for immersive visual communication. The coding process of dynamic clouds, especially video-based compression (V-PCC) developed by MPEG standardization group, is now delivering state-of-the-art performance in efficiency. V-PCC based on projection patches to 2D planes encoding sequence as texture geometry patch sequ...

The rapid development of point cloud learning has driven completion into a new era. However, the information flows most existing methods are solely feedforward, and high-level is rarely reused to improve low-level feature learning. To this end, we propose novel Feedback Network (FBNet) for completion, in which present features efficiently refined by rerouting subsequent fine-grained ones. First...