SOTAVerified

3D Object Detection

3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.

( Image credit: AVOD )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 1576 papers

TitleStatusHype
Among Us: Adversarially Robust Collaborative Perception by ConsensusCode1
BADet: Boundary-Aware 3D Object Detection from Point CloudsCode1
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object DetectionCode1
Bootstraping Clustering of Gaussians for View-consistent 3D Scene UnderstandingCode1
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object DetectionCode1
3D Bounding Box Estimation Using Deep Learning and GeometryCode1
FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object DetectionCode1
A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object DetectionCode1
3DRM:Pair-wise relation module for 3D object detectionCode1
BoxeR: Box-Attention for 2D and 3D TransformersCode1
Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point CloudCode1
Co-Fix3D: Enhancing 3D Object Detection with Collaborative RefinementCode1
Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using FusionCode1
Bridging the Domain Gap for Multi-Agent PerceptionCode1
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels OnlyCode1
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance SegmentationCode1
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object DetectionCode1
An End-to-End Transformer Model for 3D Object DetectionCode1
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection TransformersCode1
Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene FlowCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
Calibration-free BEV Representation for Infrastructure PerceptionCode1
Far3D: Expanding the Horizon for Surround-view 3D Object DetectionCode1
Canadian Adverse Driving Conditions DatasetCode1
Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D ScenesCode1
Frustum PointNets for 3D Object Detection from RGB-D DataCode1
FastPillars: A Deployment-friendly Pillar-based 3D DetectorCode1
CAPE: Camera View Position Embedding for Multi-View 3D Object DetectionCode1
FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle DetectionCode1
Fusing Event-based and RGB camera for Robust Object Detection in Adverse ConditionsCode1
Boosting 3D Object Detection via Object-Focused Image FusionCode1
Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous VehiclesCode1
Categorical Depth Distribution Network for Monocular 3D Object DetectionCode1
Exploring Active 3D Object Detection from a Generalization PerspectiveCode1
Geometry-based Distance Decomposition for Monocular 3D Object DetectionCode1
BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye ViewCode1
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty EstimationCode1
BirdNet: a 3D Object Detection Framework from LiDAR informationCode1
CenterFusion: Center-based Radar and Camera Fusion for 3D Object DetectionCode1
CenterNet3D: An Anchor Free Object Detector for Point CloudCode1
Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event CamerasCode1
CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point CloudCode1
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point CloudCode1
4D-Net for Learned Multi-Modal AlignmentCode1
Group-Free 3D Object Detection via TransformersCode1
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point CloudCode1
CoDiff: Conditional Diffusion Model for Collaborative 3D Object DetectionCode1
aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range PerceptionCode1
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object DetectionCode1
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR RepresentationsCode1
Show:102550
← PrevPage 5 of 32Next →
All datasetsnuScenesScanNetV2SUN-RGBD valKITTI Cars EasyKITTI Cars HardnuScenes Camera OnlyKITTI Cars Easy valKITTI Cars Moderate valnuscenes Camera-RadarView-of-Delft (val)KITTI Cars Hard valDAIR-V2X-I

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EA-LSSNDS0.78—Unverified
2MegFusionNDS0.77—Unverified
3MMFusion-eNDS0.77—Unverified
4BEVFusion-eNDS0.76—Unverified
5RacoonPowerNDS0.76—Unverified
6DeepInteraction-largeNDS0.76—Unverified
7DeepInteraction-eNDS0.76—Unverified
8FusionVPENDS0.75—Unverified
9FocalFormer3D-FNDS0.75—Unverified
10CenterPoint-FusionNDS0.75—Unverified