Related papers: Ada3D : Exploiting the Spatial Redundancy with Ada…

Multi-sensor fusion using LiDAR and RGB cameras significantly enhances 3D object detection task. However, conventional LiDAR sensors perform dense, stateless scans, ignoring the strong temporal continuity in real-world scenes. This leads to…

Comprehending the environment and accurately detecting objects in 3D space are essential for advancing autonomous vehicle technologies. Integrating Camera and LIDAR data has emerged as an effective approach for achieving high accuracy in 3D…

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…

Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. However, this space uses a low x, y-resolution and sacrifices…

Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial…

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…

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular…

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments.…

Adversarial robustness of BEV 3D object detectors is critical for autonomous driving (AD). Existing invasive attacks require altering the target vehicle itself (e.g. attaching patches), making them unrealistic and impractical for real-world…

Point cloud data from 3D LiDAR sensors are one of the most crucial sensor modalities for versatile safety-critical applications such as self-driving vehicles. Since the annotations of point cloud data is an expensive and time-consuming…

To enhance perception in autonomous vehicles (AVs), recent efforts are concentrating on 3D object detectors, which deliver more comprehensive predictions than traditional 2D object detectors, at the cost of increased memory footprint and…

Integrating LiDAR and Camera information into Bird's-Eye-View (BEV) has become an essential topic for 3D object detection in autonomous driving. Existing methods mostly adopt an independent dual-branch framework to generate LiDAR and camera…

Advanced Driver-Assistance Systems (ADAS) have successfully integrated learning-based techniques into vehicle perception and decision-making. However, their application in 3D lane detection for effective driving environment perception is…

Real-time detection of objects in the 3D scene is one of the tasks an autonomous agent needs to perform for understanding its surroundings. While recent Deep Learning-based solutions achieve satisfactory performance, their high…

In this paper, we propose an accurate and robust perception module for Autonomous Vehicles (AVs) for drivable space extraction. Perception is crucial in autonomous driving, where many deep learning-based methods, while accurate on benchmark…

Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adaptive focus method (AdaFocus) has achieved a favorable…

Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects…

Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D…

Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the front-surface-biased…