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 101–150 of 1576 papers

TitleStatusHype
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
PointPillars: Fast Encoders for Object Detection from Point CloudsCode2
RCooper: A Real-world Large-scale Dataset for Roadside Cooperative PerceptionCode2
RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAMCode2
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object DetectionCode2
SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object DetectionCode2
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous DrivingCode2
HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view CamerasCode2
SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large ObjectsCode2
Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionCode2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth EstimationCode2
SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera VideosCode2
DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy PredictionCode2
SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object DetectionCode2
FocalFormer3D: Focusing on Hard Instance for 3D Object DetectionCode2
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object DetectionCode2
Focal Sparse Convolutional Networks for 3D Object DetectionCode2
DeepInteraction: 3D Object Detection via Modality InteractionCode2
EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation ModelsCode2
TJ4DRadSet: A 4D Radar Dataset for Autonomous DrivingCode2
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object DetectionCode2
EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy NetworkCode2
Argoverse 2: Next Generation Datasets for Self-Driving Perception and ForecastingCode2
Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine PerceptionCode2
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View RepresentationCode2
V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative PerceptionCode2
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and BeyondCode2
BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-ViewCode2
DSVT: Dynamic Sparse Voxel Transformer with Rotated SetsCode2
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point CloudsCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object DetectionCode2
BEVFusion: A Simple and Robust LiDAR-Camera Fusion FrameworkCode2
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous DrivingCode2
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
CenterFormer: Center-based Transformer for 3D Object DetectionCode2
DiffBEV: Conditional Diffusion Model for Bird's Eye View PerceptionCode2
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object DetectionCode2
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object DetectionCode2
BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal StereoCode2
FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height PluginCode2
FocalFormer3D : Focusing on Hard Instance for 3D Object DetectionCode2
EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object DetectionCode2
Fully Test-Time Adaptation for Monocular 3D Object DetectionCode2
Fully Sparse 3D Object DetectionCode2
Generative Sparse Detection Networks for 3D Single-shot Object DetectionCode2
LISO: Lidar-only Self-Supervised 3D Object DetectionCode2
Is Your LiDAR Placement Optimized for 3D Scene Understanding?Code2
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving DataCode2
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object DetectionCode2
Show:102550
← PrevPage 3 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