Related papers: M&M3D: Multi-Dataset Training and Efficient Networ…

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

Multi-view 3D object detection (MV3D-Det) in Bird-Eye-View (BEV) has drawn extensive attention due to its low cost and high efficiency. Although new algorithms for camera-only 3D object detection have been continuously proposed, most of…

Detecting objects in 3D space using multiple cameras, known as Multi-Camera 3D Object Detection (MC3D-Det), has gained prominence with the advent of bird's-eye view (BEV) approaches. However, these methods often struggle when faced with…

Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing…

We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled source domain to an…

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation remains a critical challenge for cross-domain deployment. In…

Accurate 3D object detection is a critical component of autonomous driving, enabling vehicles to perceive their surroundings with precision and make informed decisions. LiDAR sensors, widely used for their ability to provide detailed 3D…

Vision-centric Bird's Eye View (BEV) perception holds considerable promise for autonomous driving. Recent studies have prioritized efficiency or accuracy enhancements, yet the issue of domain shift has been overlooked, leading to…

3D object detection using LiDAR data is an indispensable component for autonomous driving systems. Yet, only a few LiDAR-based 3D object detection methods leverage segmentation information to further guide the detection process. In this…

This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D…

In multi-object detection using neural networks, the fundamental problem is, "How should the network learn a variable number of bounding boxes in different input images?". Previous methods train a multi-object detection network through a…

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…

We investigate the direction of training a 3D object detector for new object classes from only 2D bounding box labels of these new classes, while simultaneously transferring information from 3D bounding box labels of the existing classes.…

Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or…

Detecting dynamic objects and predicting static road information such as drivable areas and ground heights are crucial for safe autonomous driving. Previous works studied each perception task separately, and lacked a collective quantitative…

As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited…

Existing multi-agent perception algorithms usually select to share deep neural features extracted from raw sensing data between agents, achieving a trade-off between accuracy and communication bandwidth limit. However, these methods assume…

3D visual perception tasks based on multi-camera images are essential for autonomous driving systems. Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object…

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…