Related papers: On the Robustness of 3D Object Detectors

3D object detection is fundamental for safe and robust intelligent transportation systems. Current multi-modal 3D object detectors often rely on complex architectures and training strategies to achieve higher detection accuracy. However,…

This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple…

Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challenging conditions, under which noise or perturbations are…

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works…

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…

Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed…

Convolutional Neural Networks (CNNs) have emerged as a powerful strategy for most object detection tasks on 2D images. However, their power has not been fully realised for detecting 3D objects in point clouds directly without converting…

Recent research efforts on 3D point cloud semantic segmentation (PCSS) have achieved outstanding performance by adopting neural networks. However, the robustness of these complex models have not been systematically analyzed. Given that PCSS…

There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR. The camera provides rich semantic information such as color, texture, and the LiDAR reflects the 3D shape and locations of surrounding…

Visual control policies can encounter significant performance degradation when visual conditions like lighting or camera position differ from those seen during training -- often exhibiting sharp declines in capability even for minor…

Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing…

3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to…

Recently, sparse 3D convolutions have changed 3D object detection. Performing on par with the voting-based approaches, 3D CNNs are memory-efficient and scale to large scenes better. However, there is still room for improvement. With a…

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during…

The recent success of neural networks enables a better interpretation of 3D point clouds, but processing a large-scale 3D scene remains a challenging problem. Most current approaches divide a large-scale scene into small regions and combine…

Object detection is an essential task for autonomous robots operating in dynamic and changing environments. A robot should be able to detect objects in the presence of sensor noise that can be induced by changing lighting conditions for…

In autonomous driving, 3D object detection based on multi-modal data has become an indispensable approach when facing complex environments around the vehicle. During multi-modal detection, LiDAR and camera are simultaneously applied for…

Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep learning community. Most proposed methods either use rotation invariant descriptors as inputs or try to design rotation equivariant networks.…

We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture. While object detection with transformers has been an active field of research, it has proved difficult to apply such models to…

The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performance of object…