Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey
The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …
deep learning (DL). However, the latter faces various issues, including the lack of data or …
[PDF][PDF] A comprehensive survey and taxonomy on point cloud registration based on deep learning
Channel-wise and spatially-guided Multimodal feature fusion network for 3D Object Detection in Autonomous Vehicles
Accurate 3-D object detection is vital in autonomous driving. Traditional LiDAR models
struggle with sparse point clouds. We propose a novel approach integrating LiDAR and …
struggle with sparse point clouds. We propose a novel approach integrating LiDAR and …
[HTML][HTML] PLC-fusion: perspective-based hierarchical and deep lidar camera fusion for 3D object detection in autonomous vehicles
Accurate 3D object detection is essential for autonomous driving, yet traditional LiDAR
models often struggle with sparse point clouds. We propose perspective-aware hierarchical …
models often struggle with sparse point clouds. We propose perspective-aware hierarchical …
FlyCore: Fast Low-frequency Coarse Registration of Large-scale Outdoor LiDAR Point Clouds
Fast and accurate registration of outdoor LiDAR point clouds poses a considerable
challenge for their large-scale (eg, 300 K points) and intricate (eg, noise and outliers) …
challenge for their large-scale (eg, 300 K points) and intricate (eg, noise and outliers) …
An adaptive point cloud registration method with self-cross attention and hierarchical correspondence filtering
Z Lian, Y Gu, K You, X **e, M Guo, Y Gu… - Optics & Laser Technology, 2025 - Elsevier
Robust cross-source point cloud (CSPC) registration is a formidable task due to the huge
differences in point cloud data collected by multi-source sensors. We propose a point cloud …
differences in point cloud data collected by multi-source sensors. We propose a point cloud …
EADReg: Probabilistic Correspondence Generation with Efficient Autoregressive Diffusion Model for Outdoor Point Cloud Registration
Diffusion models have shown the great potential in the point cloud registration (PCR) task,
especially for enhancing the robustness to challenging cases. However, existing diffusion …
especially for enhancing the robustness to challenging cases. However, existing diffusion …
Robust Point Cloud Registration via Patch Matching
T Zhao, T Tian, X Zou, L Yan… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
We study the problem of exacting accurate correspondence pairs for point cloud registration.
The existing correspondence methods focus on constructing point descriptors and then …
The existing correspondence methods focus on constructing point descriptors and then …
DBDNet: Partial-to-partial point cloud registration with dual branches decoupling
Point cloud registration plays a crucial role in various computer vision tasks. In this paper,
we concentrate on two aspects of the point cloud registration problem: rotation–translation …
we concentrate on two aspects of the point cloud registration problem: rotation–translation …