Related papers: PARE-Net: Position-Aware Rotation-Equivariant Netw…

Equivariant representation learning aims to capture variations induced by input transformations in the representation space, whereas invariant representation learning encodes semantic information by disregarding such transformations. Recent…

This paper introduces a new method for 3D point cloud registration based on deep learning. The architecture is composed of three distinct blocs: (i) an encoder composed of a convolutional graph-based descriptor that encodes the immediate…

The rotation robustness property has drawn much attention to point cloud analysis, whereas it still poses a critical challenge in 3D object detection. When subjected to arbitrary rotation, most existing detectors fail to produce expected…

This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features under certain…

This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net…

We present a novel rotation invariant architecture operating directly on point cloud data. We demonstrate how rotation invariance can be injected into a recently proposed point-based PCNN architecture, at all layers of the network,…

Place recognition plays an important role in achieving robust long-term autonomy. Real-world robots face a wide range of weather conditions (e.g. overcast, heavy rain, and snowing) and most sensors (i.e. camera, LiDAR) essentially…

Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in…

Despite recent advances in facial recognition, there remains a fundamental issue concerning degradations in performance due to substantial perspective (pose) differences between enrollment and query (probe) imagery. Therefore, we propose a…

In this work, we propose a novel framework named Region-Aware Network (RANet), which learns the ability of anti-confusing in case of heavy occlusion, nearby person and symmetric appearance, for human pose estimation. Specifically, the…

Iterative Closest Point (ICP) solves the rigid point cloud registration problem iteratively in two steps: (1) make hard assignments of spatially closest point correspondences, and then (2) find the least-squares rigid transformation. The…

Recently, object detection in aerial images has gained much attention in computer vision. Different from objects in natural images, aerial objects are often distributed with arbitrary orientation. Therefore, the detector requires more…

Point cloud registration is a fundamental step for many tasks. In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual…

LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively, offering complementary advantages and heterogeneous. Due to the fundamental differences in sensing mechanisms, spatial…

Point cloud registration plays a critical role in a multitude of computer vision tasks, such as pose estimation and 3D localization. Recently, a plethora of deep learning methods were formulated that aim to tackle this problem. Most of…

Efficiency and robustness are increasingly needed for applications on 3D point clouds, with the ubiquitous use of edge devices in scenarios like autonomous driving and robotics, which often demand real-time and reliable responses. The paper…

In recent years, learning-based image registration methods have gradually moved away from direct supervision with target warps to instead use self-supervision, with excellent results in several registration benchmarks. These approaches…

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…

Many applications require the robustness, or ideally the invariance, of a neural network to certain transformations of input data. Most commonly, this requirement is addressed by either augmenting the training data, using adversarial…

Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While…