Deep hough voting for 3d object detection in point clouds
Current 3D object detection methods are heavily influenced by 2D detectors. In order to
leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids …
leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids …
Imvotenet: Boosting 3d object detection in point clouds with image votes
Abstract 3D object detection has seen quick progress thanks to advances in deep learning
on point clouds. A few recent works have even shown state-of-the-art performance with just …
on point clouds. A few recent works have even shown state-of-the-art performance with just …
Go-ICP: A globally optimal solution to 3D ICP point-set registration
The Iterative Closest Point (ICP) algorithm is one of the most widely used methods for point-
set registration. However, being based on local iterative optimization, ICP is known to be …
set registration. However, being based on local iterative optimization, ICP is known to be …
A survey of simple geometric primitives detection methods for captured 3D data
A Kaiser, JA Ybanez Zepeda… - Computer Graphics …, 2019 - Wiley Online Library
The amount of captured 3D data is continuously increasing, with the democratization of
consumer depth cameras, the development of modern multi‐view stereo capture setups and …
consumer depth cameras, the development of modern multi‐view stereo capture setups and …
Fast descriptors and correspondence propagation for robust global point cloud registration
In this paper, we present a robust global approach for point cloud registration from uniformly
sampled points. Based on eigenvalues and normals computed from multiple scales, we …
sampled points. Based on eigenvalues and normals computed from multiple scales, we …
Gogma: Globally-optimal gaussian mixture alignment
D Campbell, L Petersson - Proceedings of the IEEE …, 2016 - openaccess.thecvf.com
Gaussian mixture alignment is a family of approaches that are frequently used for robustly
solving the point-set registration problem. However, since they use local optimisation, they …
solving the point-set registration problem. However, since they use local optimisation, they …
3D pose estimation of daily objects using an RGB-D camera
C Choi, HI Christensen - 2012 IEEE/RSJ International …, 2012 - ieeexplore.ieee.org
In this paper, we present an object pose estimation algorithm exploiting both depth and color
information. While many approaches assume that a target region is cleanly segmented from …
information. While many approaches assume that a target region is cleanly segmented from …
Learning generalizable part-based feature representation for 3d point clouds
Deep networks on 3D point clouds have achieved remarkable success in 3D classification,
while they are vulnerable to geometry variations caused by inconsistent data acquisition …
while they are vulnerable to geometry variations caused by inconsistent data acquisition …
ICP registration with DCA descriptor for 3D point clouds
Y He, J Yang, X Hou, S Pang, J Chen - Optics express, 2021 - opg.optica.org
Widely used in three-dimensional (3D) modeling, reverse engineering and other fields, point
cloud registration aims to find the translation and rotation matrix between two point clouds …
cloud registration aims to find the translation and rotation matrix between two point clouds …
[HTML][HTML] Recognizing geometric primitives in 3D point clouds of mechanical CAD objects
The problem faced in this paper concerns the recognition of simple and complex geometric
primitives in point clouds resulting from scans of mechanical CAD objects. A large number of …
primitives in point clouds resulting from scans of mechanical CAD objects. A large number of …