A new method for point cloud registration: Adaptive relation-oriented convolution and recurrent correspondence-walk
F Cao, L Zhu, H Ye, C Wen, Q Zhang - Knowledge-Based Systems, 2024 - Elsevier
For point cloud registration (PCR), a matching matrix is critical. Unfortunately, the existing
approaches do not explicitly devise schemes to refine the matching matrix. Furthermore …
approaches do not explicitly devise schemes to refine the matching matrix. Furthermore …
PointDifformer: Robust point cloud registration with neural diffusion and transformer
Point cloud registration is a fundamental technique in 3-D computer vision with applications
in graphics, autonomous driving, and robotics. However, registration tasks under …
in graphics, autonomous driving, and robotics. However, registration tasks under …
TD-NeRF: transfer learning and diffusion regulation based NeRF for scene perception
W Hu, C Tian, L Wen, H Ding - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Scene perception based on 3D reconstruction has been widely applied in various
downstream applications for intelligent devices. The use of deep learning methods for scene …
downstream applications for intelligent devices. The use of deep learning methods for scene …
Noise Model Based Line Segmentation for Plane Extraction in Sparse 3D LiDAR Data
L He, B Li - IEEE Transactions on Geoscience and Remote …, 2024 - ieeexplore.ieee.org
Planar features serve as an important component in point cloud registration and
reconstruction. However, extracting planes in the point clouds collected by a 3-D LiDAR …
reconstruction. However, extracting planes in the point clouds collected by a 3-D LiDAR …
IPAL: Infinite Planes as Lines for Consistent Mapping in Indoor Multi-floor Environments
Indoor high-precision maps are harder to obtain. Numerous researchers considered the
extendibility of indoor plane features to constrain the poses and improve mapping …
extendibility of indoor plane features to constrain the poses and improve mapping …