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 301–350 of 1576 papers

TitleStatusHype
Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene FlowCode1
Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object DetectionCode1
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
Fully Sparse Fusion for 3D Object DetectionCode1
Density-Insensitive Unsupervised Domain Adaption on 3D Object DetectionCode1
MetaBEV: Solving Sensor Failures for BEV Detection and Map SegmentationCode1
Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation LogisticsCode1
RadarGNN: Transformation Invariant Graph Neural Network for Radar-based PerceptionCode1
Curricular Object Manipulation in LiDAR-based Object DetectionCode1
MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object DetectionCode1
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object DetectionCode1
Open-Vocabulary Point-Cloud Object Detection without 3D AnnotationCode1
CRN: Camera Radar Net for Accurate, Robust, Efficient 3D PerceptionCode1
Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object PredictionCode1
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision TransformerCode1
Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous DrivingCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object DetectionCode1
LinK: Linear Kernel for LiDAR-based 3D PerceptionCode1
UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye ViewCode1
Viewpoint Equivariance for Multi-View 3D Object DetectionCode1
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-TrainingCode1
VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object DetectionCode1
GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D UnderstandingCode1
Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor LocalizationCode1
Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow PredictionCode1
CAPE: Camera View Position Embedding for Multi-View 3D Object DetectionCode1
Among Us: Adversarially Robust Collaborative Perception by ConsensusCode1
MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud SequencesCode1
PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object DetectionCode1
ReBound: An Open-Source 3D Bounding Box Annotation Tool for Active LearningCode1
DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object DetectionCode1
Calibration-free BEV Representation for Infrastructure PerceptionCode1
BSH-Det3D: Improving 3D Object Detection with BEV Shape HeatmapCode1
FastPillars: A Deployment-friendly Pillar-based 3D DetectorCode1
LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object DetectionCode1
On the Adversarial Robustness of Camera-based 3D Object DetectionCode1
Exploring Active 3D Object Detection from a Generalization PerspectiveCode1
Unleash the Potential of Image Branch for Cross-modal 3D Object DetectionCode1
SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded NetworkCode1
Rethinking Voxelization and Classification for 3D Object DetectionCode1
FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D DetectionCode1
Object as Query: Lifting any 2D Object Detector to 3D DetectionCode1
Learning from Noisy Data for Semi-Supervised 3D Object DetectionCode1
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object DetectionCode1
A Fast Unified System for 3D Object Detection and TrackingCode1
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU SupervisionCode1
Benchmarking Robustness of 3D Object Detection to Common CorruptionsCode1
CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited AnnotationsCode1
TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry LearningCode1
Show:102550
← PrevPage 7 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