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 151–200 of 1576 papers

TitleStatusHype
NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance FieldsCode2
nuScenes: A multimodal dataset for autonomous drivingCode2
Objects as PointsCode2
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with TransformersCode2
OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality PropagationCode2
ARM3D: Attention-based relation module for indoor 3D object detectionCode1
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D DataCode1
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object DetectionCode1
4D-Net for Learned Multi-Modal AlignmentCode1
DiffuBox: Refining 3D Object Detection with Point DiffusionCode1
Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D SceneCode1
3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object DetectionCode1
FastPillars: A Deployment-friendly Pillar-based 3D DetectorCode1
FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object DetectionCode1
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object DetectionCode1
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object DetectionCode1
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D DetectionCode1
Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain RobustnessCode1
Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using FusionCode1
Densely Constrained Depth Estimator for Monocular 3D Object DetectionCode1
Delving into Motion-Aware Matching for Monocular 3D Object TrackingCode1
Density-Insensitive Unsupervised Domain Adaption on 3D Object DetectionCode1
Deformable PV-RCNN: Improving 3D Object Detection with Learned DeformationsCode1
3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance SegmentationCode1
Delving into Localization Errors for Monocular 3D Object DetectionCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object DetectionCode1
FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle DetectionCode1
Deep Hough Voting for 3D Object Detection in Point CloudsCode1
3D Spatial Recognition without Spatially Labeled 3DCode1
Exploring Active 3D Object Detection from a Generalization PerspectiveCode1
An End-to-End Transformer Model for 3D Object DetectionCode1
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance SegmentationCode1
SeSame: Simple, Easy 3D Object Detection with Point-Wise SemanticsCode1
Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point CloudCode1
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU SupervisionCode1
3DRM:Pair-wise relation module for 3D object detectionCode1
A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object DetectionCode1
3D Cascade RCNN: High Quality Object Detection in Point CloudsCode1
FADet: A Multi-sensor 3D Object Detection Network based on Local Featured AttentionCode1
Among Us: Adversarially Robust Collaborative Perception by ConsensusCode1
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object DetectionCode1
3D Bounding Box Estimation Using Deep Learning and GeometryCode1
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels OnlyCode1
Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene FlowCode1
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection TransformersCode1
DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object DetectionCode1
Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event CamerasCode1
Boosting 3D Object Detection via Object-Focused Image FusionCode1
Show:102550
← PrevPage 4 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
2MMFusion-eNDS0.77—Unverified
3MegFusionNDS0.77—Unverified
4RacoonPowerNDS0.76—Unverified
5BEVFusion-eNDS0.76—Unverified
6DeepInteraction-largeNDS0.76—Unverified
7DeepInteraction-eNDS0.76—Unverified
8DAANDS0.75—Unverified
9FusionVPENDS0.75—Unverified
10CenterPoint-FusionNDS0.75—Unverified