相关论文: 3D Point Cloud Completion with Geometric-Aware Adv…

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds…

Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensively studied, but…

Anomaly detection, which is a critical and popular topic in computer vision, aims to detect anomalous samples that are different from the normal (i.e., non-anomalous) ones. The current mainstream methods focus on anomaly detection for…

Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbations. In this paper, we delve into boosting the general…

This work presents a generative adversarial architecture for generating three-dimensional shapes based on signed distance representations. While the deep generation of shapes has been mostly tackled by voxel and surface point cloud…

As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better…

In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-structured graph…

In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a…

Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. To bridge this gap,…

Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Adversarial training, especially projected gradient descent (PGD), has proven to be a successful approach for improving robustness against adversarial attacks. After adversarial training, gradients of models with respect to their inputs…

Since real-world training datasets cannot properly sample the long tail of the underlying data distribution, corner cases and rare out-of-domain samples can severely hinder the performance of state-of-the-art models. This problem becomes…

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…

Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many downstream tasks such as scene graph aided point cloud…

Processing large point clouds is a challenging task. Therefore, the data is often downsampled to a smaller size such that it can be stored, transmitted and processed more efficiently without incurring significant performance degradation.…

We propose a mechanism to reconstruct part annotated 3D point clouds of objects given just a single input image. We demonstrate that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks,…

Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard…

The application of deep learning to 3D point clouds is challenging due to its lack of order. Inspired by the point embeddings of PointNet and the edge embeddings of DGCNNs, we propose three improvements to the task of point cloud analysis.…

Performances on standard 3D point cloud benchmarks have plateaued, resulting in oversized models and complex network design to make a fractional improvement. We present an alternative to enhance existing deep neural networks without any…