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 401–450 of 1576 papers

TitleStatusHype
SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and TrackingCode1
Real3D-Aug: Point Cloud Augmentation by Placing Real Objects with Occlusion Handling for 3D Detection and SegmentationCode1
MonoGround: Detecting Monocular 3D Objects from the GroundCode1
Learning Ego 3D Representation as Ray TracingCode1
Voxel Field Fusion for 3D Object DetectionCode1
itKD: Interchange Transfer-based Knowledge Distillation for 3D Object DetectionCode1
Towards Efficient 3D Object Detection with Knowledge DistillationCode1
Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object DetectionCode1
PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D DetectionCode1
3D Object Detection with a Self-supervised Lidar Scene Flow BackboneCode1
PolyLoss: A Polynomial Expansion Perspective of Classification Loss FunctionsCode1
Spatiality-guided Transformer for 3D Dense Captioning on Point CloudsCode1
Multimodal Token Fusion for Vision TransformersCode1
OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR DataCode1
DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D DetectorsCode1
RBGNet: Ray-based Grouping for 3D Object DetectionCode1
ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression FrameworkCode1
STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded ScenesCode1
Homography Loss for Monocular 3D Object DetectionCode1
Fusing Event-based and RGB camera for Robust Object Detection in Adverse ConditionsCode1
LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object DetectionCode1
Point2Seq: Detecting 3D Objects as SequencesCode1
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D PerceptionCode1
MonoDTR: Monocular 3D Object Detection with Depth-Aware TransformerCode1
Stereo Neural Vernier CaliperCode1
VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial AttentionCode1
WeakM3D: Towards Weakly Supervised Monocular 3D Object DetectionCode1
MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object DetectionCode1
PillarGrid: Deep Learning-based Cooperative Perception for 3D Object Detection from Onboard-Roadside LiDARCode1
Point Density-Aware Voxels for LiDAR 3D Object DetectionCode1
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label EnhancementCode1
Pseudo-Stereo for Monocular 3D Object Detection in Autonomous DrivingCode1
CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point CloudCode1
ARM3D: Attention-based relation module for indoor 3D object detectionCode1
3DRM:Pair-wise relation module for 3D object detectionCode1
3D Object Detection from Images for Autonomous Driving: A SurveyCode1
MonoDistill: Learning Spatial Features for Monocular 3D Object DetectionCode1
Attention-based Proposals Refinement for 3D Object DetectionCode1
End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and LocalizationCode1
SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object DetectionCode1
Point Cloud Pre-Training With Natural 3D StructuresCode1
Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar NetworkCode1
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object DetectionCode1
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object DetectionCode1
SoK: Vehicle Orientation Representations for Deep Rotation EstimationCode1
Behind the Curtain: Learning Occluded Shapes for 3D Object DetectionCode1
SGM3D: Stereo Guided Monocular 3D Object DetectionCode1
Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object DetectionCode1
BoxeR: Box-Attention for 2D and 3D TransformersCode1
Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Point Density Level EstimationCode1
Show:102550
← PrevPage 9 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