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

Showing 101125 of 1576 papers

TitleStatusHype
Virtual Sparse Convolution for Multimodal 3D Object DetectionCode2
Pillar R-CNN for Point Cloud 3D Object DetectionCode2
DSVT: Dynamic Sparse Voxel Transformer with Rotated SetsCode2
Argoverse 2: Next Generation Datasets for Self-Driving Perception and ForecastingCode2
FocalFormer3D: Focusing on Hard Instance for 3D Object DetectionCode2
MegaPose: 6D Pose Estimation of Novel Objects via Render & CompareCode2
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world LearningCode2
Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal FusionCode2
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object DetectionCode2
Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence MapsCode2
BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal StereoCode2
CenterFormer: Center-based Transformer for 3D Object DetectionCode2
DeepInteraction: 3D Object Detection via Modality InteractionCode2
PolarMix: A General Data Augmentation Technique for LiDAR Point CloudsCode2
Monocular 3D Object Detection with Depth from MotionCode2
Omni3D: A Large Benchmark and Model for 3D Object Detection in the WildCode2
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object DetectionCode2
Fully Sparse 3D Object DetectionCode2
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse TransformersCode2
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNsCode2
Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy AutoencodersCode2
3D Object Detection for Autonomous Driving: A Comprehensive SurveyCode2
K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather ConditionsCode2
LinK3D: Linear Keypoints Representation for 3D LiDAR Point CloudCode2
Show:102550
← PrevPage 5 of 64Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EA-LSSNDS0.78Unverified
2MMFusion-eNDS0.77Unverified
3MegFusionNDS0.77Unverified
4RacoonPowerNDS0.76Unverified
5BEVFusion-eNDS0.76Unverified
6DeepInteraction-largeNDS0.76Unverified
7DeepInteraction-eNDS0.76Unverified
8DAANDS0.75Unverified
9FusionVPENDS0.75Unverified
10CenterPoint-FusionNDS0.75Unverified