J Lin, Z Wei, C Ding, K Jia - European Conference on Computer Vision, 2022 - Springer
It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, eg, category-level 6D object pose …
The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field. The transformer has been used as a …
H Li, J Lin, K Jia - European Conference on Computer Vision, 2022 - Springer
Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses. However, surrogate objectives of correspondence …
D Huang, Y Chen, Y Ding, J Liao, J Liu, K Wu… - arXiv preprint arXiv …, 2022 - arxiv.org
Bird's eye view (BEV) is widely adopted by most of the current point cloud detectors due to the applicability of well-explored 2D detection techniques. However, existing methods obtain …
Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models …
X Wei, Y Liu, J Li, H Chu, Z Zhang, F Tan, P Hu - Neurocomputing, 2022 - Elsevier
Convolutional neural networks (CNNs) have been extensively used in a number of applications and have shown to be quite effective. As the depth and width of the network …
L Yin, W Tian, L Wang, Z Wang, Z Yu - Remote Sensing, 2022 - mdpi.com
Recently, 3D object detection based on multi-modal sensor fusion has been increasingly adopted in automated driving and robotics. For example, the semantic information provided …
Urban mobility is undergoing a paradigm shift due to increasing concerns about road safety, environmental impact, and traffic efficiency. Addressing these challenges, this thesis fosters …
GK Erabati, H Araujo - CenterPoint - openaccess.thecvf.com
Our model mainly consists of two modules: CNN backbone and transformer encoder- decoder. We test with SparseConv [6] and PointPillars [7] with SECOND [14] as feature …