Related papers: CoFiNet: Reliable Coarse-to-fine Correspondences f…

Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view…

We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates…

The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance,…

Rigid registration of point clouds is a fundamental problem in computer vision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, conventional methods like…

There is a growing number of tasks that work directly on point clouds. As the size of the point cloud grows, so do the computational demands of these tasks. A possible solution is to sample the point cloud first. Classic sampling…

Diffusion models are a powerful framework for tackling ill-posed problems, with recent advancements extending their use to point cloud upsampling. Despite their potential, existing diffusion models struggle with inefficiencies as they map…

Compressing a set of unordered points is far more challenging than compressing images/videos of regular sample grids, because of the difficulties in characterizing neighboring relations in an irregular layout of points. Many researchers…

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic…

Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a new point cloud processing scheme and backbone, called…

As a fundamental problem in computer vision, point cloud registration aims to seek the optimal transformation for aligning a pair of point clouds. In most existing methods, the information flows are usually forward transferring, thus…

Point cloud compression (PCC) is a key enabler for various 3-D applications, owing to the universality of the point cloud format. Ideally, 3D point clouds endeavor to depict object/scene surfaces that are continuous. Practically, as a set…

Network alignment, or the task of finding corresponding nodes in different networks, is an important problem formulation in many application domains. We propose CAPER, a multilevel alignment framework that Coarsens the input graphs, Aligns…

In this paper, we present a novel method Coarse- and Fine-grained Attention Network (CFANet) for generating high-quality crowd density maps and people count estimation by incorporating attention maps to better focus on the crowd area. We…

Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking…

In recent years, decentralized sensor networks have garnered significant attention in the field of state estimation owing to enhanced robustness, scalability, and fault tolerance. Optimal fusion performance can be achieved under fully…

Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping…

Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view with dynamic objects, environmental noise, or other…

Point cloud registration is a fundamental problem in computer vision that aims to estimate the transformation between corresponding sets of points. Non-rigid registration, in particular, involves addressing challenges including various…

We present RoarNet, a new approach for 3D object detection from a 2D image and 3D Lidar point clouds. Based on two-stage object detection framework with PointNet as our backbone network, we suggest several novel ideas to improve 3D object…

In order to achieve better performance for point cloud analysis, many researchers apply deeper neural networks using stacked Multi-Layer-Perceptron (MLP) convolutions over irregular point cloud. However, applying dense MLP convolutions over…