3D object detection for autonomous driving using LiDAR, cameras, or sensor fusion — 3D bounding boxes, object classification, velocity estimation and tracking.
We introduce a framework that characterizes visual scene variations in the frequency domain and uses them to synthesize diverse source-domain views.
Engineering 5.0 · Research 7.0 · Business 5.0
Multimodal 3D object detection based on LiDAR and cameras has demonstrated excellent performance in ground-vehicle scenarios, but has not been explored for Unmanned Aerial Vehicle (UAV) platforms.
Engineering 5.0 · Research 7.0 · Business 5.0
We propose ``Ask The Neighbor'' (ATN3D), a LiDAR-Radar framework tailored for sparse-range conditions.
Engineering 5.5 · Research 7.0 · Business 5.5
To bridge this gap, we propose Distortion-Aware PETR (DAPETR), a projection-free detector tailored for mixed pinhole-fisheye camera setups.
Engineering 5.0 · Research 7.0 · Business 5.0
We present StandardE2E, a framework that provides a single unified interface over E2E driving datasets.
Engineering 7.5 · Research 7.0 · Business 6.0
To validate the effectiveness of our approach, we construct a dedicated dataset of unstructured scenes collected from open-pit mines.
Engineering 5.5 · Research 8.0 · Business 5.0
Post-processing is a critical stage in LiDAR-based 3D object detection, where dense and overlapping proposals must be filtered for compact and reliable perception.
Engineering 7.0 · Research 7.0 · Business 5.0
In this paper, we propose PillarDETR, a novel end-to-end 3D object detection architecture that combines the efficiency of pillar-based LiDAR encoding with the representational power of modern 2D vision models.
Engineering 6.0 · Research 8.0 · Business 5.0
An autonomous driving research paper: Occlusion-aware multi-modal 3D object detection via multi-stage cross-modal fusion.
Engineering 5.0 · Research 7.0 · Business 5.0
To overcome these challenges, we propose ACF4D, a novel temporal fusion framework designed for multi-view 3D object detection.
Engineering 5.5 · Research 8.0 · Business 5.0
To address this issue, we propose a pose-aware BEV feature refinement method for post-fusion BEV representations.
Engineering 5.5 · Research 7.0 · Business 6.5
To address these issues, we propose SDEF-BEV, a novel spatial-aware dual-expert fusion network.
Engineering 5.5 · Research 8.0 · Business 5.0
To address these limitations, we introduce TPS-Drive, a novel framework centered on Task-Guided Representation Purification that empowers VLMs to Think in Purified Space.
Engineering 5.5 · Research 8.0 · Business 5.0
Accurate 3D bird's-eye view (BEV) object detection is essential for autonomous driving, and depends strongly on effective multimodal representations from complementary sensors such as cameras and LiDAR.
Engineering 5.5 · Research 7.0 · Business 5.0
To overcome this limitation, this paper proposes a fuzzy outlier removal (FOR) method based on fuzzy theory and informativeness.
Engineering 5.5 · Research 7.0 · Business 5.0
To address this and advance sustainable autonomous driving, this paper proposes a Bird’s-Eye View (BEV)-based multi-modal 3D object detection approach tailored for nighttime scenarios, integrating low-light adaptive components while preserving the original BEV pipeline.
Engineering 6.0 · Research 8.0 · Business 6.0
To address this, we propose leveraging Vehicle-to-Everything (V2X) communication to partially offload processing to the cloud, where compute resources are abundant, thus reducing overall latency.
Engineering 6.0 · Research 7.0 · Business 5.5
In this paper, we explore a frequency domain BEV representation to address these challenges and propose the FreqBEV-V2I framework that incorporates FreqBEVFlow and FreqBEVFusion blocks.
Engineering 7.0 · Research 8.0 · Business 5.5
An autonomous driving research paper: Point cloud-based multi-target 3D object detection using LiDAR sensor and deep learning.
Engineering 5.0 · Research 7.0 · Business 5.0
To address this, we propose Risk-intent Selective detection (RiSe), an interaction-aware framework that shifts the paradigm from identifying visible regions to prioritizing risk-critical ones.
Engineering 5.0 · Research 8.0 · Business 5.0