Related papers: xModel-KD: Cross-modal Knowledge Distillation for …

Point clouds analysis has grasped researchers' eyes in recent years, while 3D semantic segmentation remains a problem. Most deep point clouds models directly conduct learning on 3D point clouds, which will suffer from the severe sparsity…

Visual localization plays an important role for intelligent robots and autonomous driving, especially when the accuracy of GNSS is unreliable. Recently, camera localization in LiDAR maps has attracted more and more attention for its low…

Robust road segmentation is a key challenge in self-driving research. Though many image-based methods have been studied and high performances in dataset evaluations have been reported, developing robust and reliable road segmentation is…

Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works…

Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation…

3D point cloud segmentation faces practical challenges due to the computational complexity and deployment limitations of large-scale transformer-based models. To address this, we propose a novel Structure- and Relation-aware Knowledge…

Cross-modality registration between 2D images from cameras and 3D point clouds from LiDARs is a crucial task in computer vision and robotic. Previous methods estimate 2D-3D correspondences by matching point and pixel patterns learned by…

This paper presents a new approach to 3D object detection that leverages the properties of the data obtained by a LiDAR sensor. State-of-the-art detectors use neural network architectures based on assumptions valid for camera images.…

Point clouds are the native output of many real-world 3D sensors. To borrow the success of 2D convolutional network architectures, a majority of popular 3D perception models voxelize the points, which can result in a loss of local geometric…

3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…

Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Recent works introduce self-supervised cross-modal knowledge…

An accurate and rapid-response perception system is fundamental for autonomous vehicles to operate safely. 3D object detection methods handle point clouds given by LiDAR sensors to provide accurate depth and position information for each…

LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…

High-performance Radar-Camera 3D object detection can be achieved by leveraging knowledge distillation without using LiDAR at inference time. However, existing distillation methods typically transfer modality-specific features directly to…

Recent developments and the beginning market introduction of high-resolution imaging 4D (3+1D) radar sensors have initialized deep learning-based radar perception research. We investigate deep learning-based models operating on radar point…

In recent years, cross-modal domain adaptation has been studied on the paired 2D image and 3D LiDAR data to ease the labeling costs for 3D LiDAR semantic segmentation (3DLSS) in the target domain. However, in such a setting the paired 2D…

LiDAR scanning for surveying applications acquire measurements over wide areas and long distances, which produces large-scale 3D point clouds with significant local density variations. While existing 3D semantic segmentation models conduct…

LiDAR and camera, as two different sensors, supply geometric (point clouds) and semantic (RGB images) information of 3D scenes. However, it is still challenging for existing methods to fuse data from the two cross sensors, making them…

High-quality surface normal can help improve geometry estimation in problems faced by autonomous vehicles, such as collision avoidance and occlusion inference. While a considerable volume of literature focuses on densely scanned indoor…

3D object detection from LiDAR point cloud is of critical importance for autonomous driving and robotics. While sequential point cloud has the potential to enhance 3D perception through temporal information, utilizing these temporal…