Related papers: GAM : Gradient Attention Module of Optimization fo…
Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…
With the tide of artificial intelligence, we try to apply deep learning to understand 3D data. Point cloud is an important 3D data structure, which can accurately and directly reflect the real world. In this paper, we propose a simple and…
In the domain of point cloud analysis, despite the significant capabilities of Graph Neural Networks (GNNs) in managing complex 3D datasets, existing approaches encounter challenges like high computational costs and scalability issues with…
Graph-based methods have proven to be effective in capturing relationships among points for 3D point cloud analysis. However, these methods often suffer from suboptimal graph structures, particularly due to sparse connections at boundary…
6D pose estimation refers to object recognition and estimation of 3D rotation and 3D translation. The key technology for estimating 6D pose is to estimate pose by extracting enough features to find pose in any environment. Previous methods…
Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud objects are typically characterized by complex, disordered, and…
Deep learning models have great potential in medical imaging, including orthodontics and skeletal maturity assessment. However, applying a model to data different from its training set can lead to unreliable predictions that may impact…
Fine-grained visual classification (FGVC) is becoming an important research field, due to its wide applications and the rapid development of computer vision technologies. The current state-of-the-art (SOTA) methods in the FGVC usually…
How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting…
We propose a method for joint detection and tracking of multiple objects in 3D point clouds, a task conventionally treated as a two-step process comprising object detection followed by data association. Our method embeds both steps into a…
Vehicle instance retrieval often requires one to recognize the fine-grained visual differences between vehicles. Besides the holistic appearance of vehicles which is easily affected by the viewpoint variation and distortion, vehicle parts…
Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional…
Point cloud registration is a fundamental task in many applications such as localization, mapping, tracking, and reconstruction. Successful registration relies on extracting robust and discriminative geometric features. Though existing…
We propose simple yet effective improvements in point representations and local neighborhood graph construction within the general framework of graph neural networks (GNNs) for 3D point cloud processing. As a first contribution, we propose…
This article presents GLIM, a 3D range-inertial localization and mapping framework with GPU-accelerated scan matching factors. The odometry estimation module of GLIM employs a combination of fixed-lag smoothing and keyframe-based point…
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, there have been significant advancements in applying attention mechanisms to point cloud analysis. However, attention module variants featured in various research papers often operate under diverse settings and tasks,…
We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activation information from multiple network layers, GAM offers…
Exploiting fine-grained semantic features on point cloud is still challenging due to its irregular and sparse structure in a non-Euclidean space. Among existing studies, PointNet provides an efficient and promising approach to learn shape…
The human brain can effortlessly recognize and localize objects, whereas current 3D object detection methods based on LiDAR point clouds still report inferior performance for detecting occluded and distant objects: the point cloud…