Recent advances and perspectives in deep learning techniques for 3D point cloud data processing

Z Ding, Y Sun, S Xu, Y Pan, Y Peng, Z Mao - Robotics, 2023 - mdpi.com
In recent years, deep learning techniques for processing 3D point cloud data have seen
significant advancements, given their unique ability to extract relevant features and handle …

Accelerating DETR convergence via semantic-aligned matching

G Zhang, Z Luo, Y Yu, K Cui… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract The recently developed DEtection TRansformer (DETR) establishes a new object
detection paradigm by eliminating a series of hand-crafted components. However, DETR …

Cross-modal orthogonal high-rank augmentation for rgb-event transformer-trackers

Z Zhu, J Hou, DO Wu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
This paper addresses the problem of cross-modal object tracking from RGB videos and
event data. Rather than constructing a complex cross-modal fusion network, we explore the …

Human-centric scene understanding for 3d large-scale scenarios

Y Xu, P Cong, Y Yao, R Chen, Y Hou… - Proceedings of the …, 2023 - openaccess.thecvf.com
Human-centric scene understanding is significant for real-world applications, but it is
extremely challenging due to the existence of diverse human poses and actions, complex …

Transformers in 3d point clouds: A survey

D Lu, Q **e, M Wei, K Gao, L Xu, J Li - arxiv preprint arxiv:2205.07417, 2022 - arxiv.org
Transformers have been at the heart of the Natural Language Processing (NLP) and
Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring …

Temporal consistent 3D lidar representation learning for semantic perception in autonomous driving

L Nunes, L Wiesmann, R Marcuzzi… - Proceedings of the …, 2023 - openaccess.thecvf.com
Semantic perception is a core building block in autonomous driving, since it provides
information about the drivable space and location of other traffic participants. For learning …

Toward robust 3d perception for autonomous vehicles: A review of adversarial attacks and countermeasures

KTY Mahima, AG Perera, S Anavatti… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
At present the perception system of autonomous vehicles is grounded on 3D vision
technologies along with deep learning to process depth information. Although deep learning …

CXTrack: Improving 3D point cloud tracking with contextual information

TX Xu, YC Guo, YK Lai… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract 3D single object tracking plays an essential role in many applications, such as
autonomous driving. It remains a challenging problem due to the large appearance variation …

Glt-t: Global-local transformer voting for 3d single object tracking in point clouds

J Nie, Z He, Y Yang, M Gao, J Zhang - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Current 3D single object tracking methods are typically based on VoteNet, a 3D region
proposal network. Despite the success, using a single seed point feature as the cue for offset …

MPCT: Multiscale point cloud transformer with a residual network

Y Wu, J Liu, M Gong, Z Liu, Q Miao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The self-attention (SA) network revisits the essence of data and has achieved remarkable
results in text processing and image analysis. SA is conceptualized as a set operator that is …