Point cloud completion aims to reconstruct detailed structures from partial observations. However, previous methods often suffered from inaccurate neighbourhood feature extraction and rough reconstruction of complex structures, which is difficult to complete detailed semantic shapes. To solve this problem, we present a method that applies dynamic transformers with adaptive neighbourhood feature fusion operations to resume complete point clouds. Firstly, we propose an adaptive neighbourhood feature extraction module, which contains a learnable global neighbourhood selection strategy and a traditional local k-nearest neighbour strategy to dynamically select neighbourhood points according to the shape of different objects. Secondly, we observed that traditional point generation methods based on folding-series operations limit their capacity of generating complex and faithful shapes. Inspired by cell division, we regard the process of reconstructing as point splitting and propose a genetic hierarchical point generation module, which means current points can inherit shape features from previous points and generate more detailed structures of their own. Extensive experiments of point cloud completion are carried out on PCN and Completion3D datasets to verify the effectiveness of our method. The average category chamfer distances of our method are 7.17(�10 −3 ) in PCN and 7.96(�10 −4 ) in Completion3D, which has better completion performance than other methods.
Streak tube
imaging lidar (STIL) can
obtain 4-D images of a target, and its performance is mainly
determined by the streak tube sensor. To obtain a large field of view,
we developed a streak tube
with a photocathode length as large as 35.3 mm, which is larger than
the commonly used ST-HDR (30 mm). At the same time, the temporal
resolution and dynamic spatial resolution are 60 ps and 12 lp/mm,
which are very suitable to obtain accurate target coordinates for 4-D
imaging. In addition, the streak tube has a high detection sensitivity
of 46 mA/W at 500 nm and, hence, prospects in remote imaging. To test
the performance of the streak tube, an underwater STIL experiment was
conducted. Echo signal processing was performed by means of a bandpass
filter and a matched filter, and then the peak detection algorithm was
used to reconstruct the image. The results indicate that a spatial
resolution better than 9 mm is achieved in the limpid water with a
depth of 20 m, and a range accuracy of 1 cm is achieved in the turbid
water with a depth of 10 m. Such a performance suggests that the
large-field streak tube is of great potential for underwater target
imaging and other remote imaging applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.