3D object detection for autonomous driving using LiDAR, cameras, or sensor fusion — 3D bounding boxes, object classification, velocity estimation and tracking.
Monocular 3D object detection spans two regimes: closed-set detectors operating within a fixed category vocabulary, and open-vocabulary detectors that localize arbitrary categories by leveraging depth foundation models for 3D geometry.
Engineering 5.5 · Research 8.5 · Business 5.0
An autonomous driving research paper: Fadet: a fusion-aware 3D detection network with cascaded feature enhancement for small object detection in autonomous driving.
Engineering 5.0 · Research 7.0 · Business 5.0
Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics.
Engineering 5.5 · Research 7.0 · Business 5.0
(2) We propose geometric saliency pillar feature encoding, which enhances point cloud structural representation via point-wise saliency weighting and multi-statistic aggregation.
Engineering 5.5 · Research 7.0 · Business 5.0
An autonomous driving research paper: TriFusion: GNN-Based Multimodal Fusion for 3D Object Detection in Autonomous Driving.
Engineering 5.0 · Research 7.0 · Business 5.0
To address these limitations, we introduce a novel multi-modal fusion network for 3D object detection, consisting of two principal components: Geometric Pseudo-Image Feature Fusion and the Feature Fusion Encoder.
Engineering 5.5 · Research 8.0 · Business 5.0
An autonomous driving research paper: MambaBEV: A BEV-Based 3D Detection Model with Mamba2.
Engineering 5.0 · Research 7.0 · Business 5.0
In this study, we propose a knowledge distillation framework that transfers object-level voxel representations from a strong teacher model to lightweight student models through selective voxel-space feature alignment.
Engineering 5.5 · Research 8.0 · Business 5.5
To achieve this, we propose the Reference Dataset Alignment Method (ReDAM) for weather intensity alignment in fog and Unified-weather-edit (inspired by Weather-edit[1]) for particle positioning alignment in rain and snow.
Engineering 5.5 · Research 7.0 · Business 5.5
The commercialization of autonomous driving relies heavily on reliable environmental perception in all-weather and all-scenario conditions.
Engineering 6.0 · Research 7.0 · Business 6.0
Collaborative perception (CP) improves autonomous-driving perception by enabling connected vehicles to exchange intermediate features via V2X.
Engineering 5.0 · Research 7.0 · Business 5.0
To mitigate this limitation, we propose RECO, a region-aware extrinsic compensation framework that corrects extrinsics using piecewise 6-DoF pose offsets.
Engineering 5.0 · Research 8.0 · Business 5.0
In this paper, we propose a novel collaborative 3D object detection framework called CoGoal3D, which extracts and refines the 3D feature gradually in a two-stage pipeline.
Engineering 7.0 · Research 8.0 · Business 5.5
This paper proposes UA-CF, an uncertainty-aware camera-LiDAR fusion framework that dynamically allocates feature-level weights according to modality reliability.
Engineering 5.0 · Research 7.0 · Business 5.0
DeeperRadar is a radar-centric, sensor-stack-conditioned framework that co-designs radar sensing and multi-modal 3D detection for autonomous mobility by learning a sparse acquisition pattern end-to-end with the fusion model.
Engineering 6.0 · Research 7.0 · Business 6.0
In this work, we present TempoCross, a 3D detection method based on instance-aware sparse representations for multimodal temporal fusion.
Engineering 5.5 · Research 7.0 · Business 5.0
An autonomous driving research paper: DSAKD: Dynamic Structure-Aware Knowledge Distillation for LiDAR 3D Object Detection.
Engineering 5.0 · Research 7.0 · Business 5.0
An autonomous driving research paper: RADAR: Radar-Centric Anchored Diffusion with Adaptive Rectification for Robust 3D Object Detection.
Engineering 5.0 · Research 7.0 · Business 5.0
To bridge this gap, we propose ViCo3D, a collaborative 3D object detection framework powered by VFMs.
Engineering 5.0 · Research 8.5 · Business 5.0
To address this limitation, we propose the Anisotropic Geometry Loss (AGL) framework.
Engineering 5.0 · Research 8.0 · Business 5.0