Progressive neighbor consistency mining for correspondence pruning

X Liu, J Yang - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
The goal of correspondence pruning is to recognize correct correspondences (inliers) from
initial ones, with applications to various feature matching based tasks. Seeking neighbors in …

3-D HANet: A flexible 3-D heatmap auxiliary network for object detection

Q Xia, Y Chen, G Cai, G Chen, D Xie… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
3-D object detection is a vital part of outdoor scene perception. Learning the complete size
and accurate positioning of objects from an incomplete point cloud spatial structure is …

3WM-AugNet: A Feature Augmentation Network for Remote Sensing Ship Detection Based on Three-way Decisions and Multi-granularity

L Ying, D Miao, Z Zhang - IEEE Transactions on Geoscience …, 2023 - ieeexplore.ieee.org
With the continuous advancement of remote sensing (RS) technology, RS ship detection
plays a crucial role in ensuring maritime safety and the oceanic economy, but it also faces …

Evolutionary channel pruning for real-time object detection

C Yang, Z Lin, Z Lan, R Chen, L Wei, Y Liu - Knowledge-Based Systems, 2024 - Elsevier
Real-time object detection plays a crucial role in edge devices applications. Pruning
methods are usually used to effectively eliminate redundant parameters of the object …

PG-net: Progressive guidance network via robust contextual embedding for efficient point cloud registration

J Wang, X Liu, L Dai, J Ma, L Wei… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Building high-quality correspondences is critical in the feature-based point cloud registration
pipelines. However, existing single-sequence learning frameworks are difficult to accurately …

Local feature matching using deep learning: A survey

S Xu, S Chen, R Xu, C Wang, P Lu, L Guo - Information Fusion, 2024 - Elsevier
Local feature matching enjoys wide-ranging applications in the realm of computer vision,
encompassing domains such as image retrieval, 3D reconstruction, and object recognition …

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning

Y Liu, W Zhou, Y Li, S Zhao - Proceedings of the 32nd ACM International …, 2024 - dl.acm.org
Correspondence pruning has recently drawn considerable attention as a crucial step in
image matching. Existing methods typically achieve this by constructing neighborhoods for …

Multi-granularity-Aware Network for SAR Ship Detection in Complex Backgrounds

L Ying, Y Liu, Z Zhang, D Miao - IEEE Geoscience and Remote …, 2024 - ieeexplore.ieee.org
Synthetic aperture radar (SAR) is a vital tool for ship detection, as it acquires high-resolution
remote sensing images when optical images cannot penetrate. However, two primary …

Guided sampling for multistructure data via neighborhood consensus and residual sorting

T Lai, Y Liu, J Chang, L Wei, Z Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Robust model fitting is a critical technique for artificial intelligence. The performance of most
robust model fitting techniques heavily depends on the use of sampling algorithms. In this …

CSCE-Net: Channel-spatial contextual enhancement network for robust point cloud registration

J Wang, C Yang, L Wei, R Chen - Remote Sensing, 2022 - mdpi.com
Seeking reliable correspondences between two scenes is crucial for solving feature-based
point cloud registration tasks. In this paper, we propose a novel outlier rejection network …