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 51–100 of 1576 papers

TitleStatusHype
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision TransformerCode2
Fully Test-Time Adaptation for Monocular 3D Object DetectionCode2
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and BeyondCode2
ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided TransformersCode2
Commonsense Prototype for Outdoor Unsupervised 3D Object DetectionCode2
Scaling Multi-Camera 3D Object Detection through Weak-to-Strong ElicitingCode2
MonoCD: Monocular 3D Object Detection with Complementary DepthsCode2
HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view CamerasCode2
NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance FieldsCode2
SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large ObjectsCode2
OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality PropagationCode2
Is Your LiDAR Placement Optimized for 3D Scene Understanding?Code2
RCooper: A Real-world Large-scale Dataset for Roadside Cooperative PerceptionCode2
MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation LearningCode2
LISO: Lidar-only Self-Supervised 3D Object DetectionCode2
SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object DetectionCode2
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object DetectionCode2
MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object DetectionCode2
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object DetectionCode2
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object DetectionCode2
MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object DetectionCode2
RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAMCode2
WidthFormer: Toward Efficient Transformer-based BEV View TransformationCode2
OneFormer3D: One Transformer for Unified Point Cloud SegmentationCode2
FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height PluginCode2
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training ParadigmCode2
UniPAD: A Universal Pre-training Paradigm for Autonomous DrivingCode2
CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object DetectionCode2
SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera VideosCode2
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View RepresentationCode2
FocalFormer3D : Focusing on Hard Instance for 3D Object DetectionCode2
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object DetectionCode2
Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine PerceptionCode2
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point CloudsCode2
SAM3D: Zero-Shot 3D Object Detection via Segment Anything ModelCode2
UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous DrivingCode2
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point CloudsCode2
OctFormer: Octree-based Transformers for 3D Point CloudsCode2
TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene UnderstandingCode2
SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object DetectionCode2
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene UnderstandingCode2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth EstimationCode2
EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object DetectionCode2
Spherical Transformer for LiDAR-based 3D RecognitionCode2
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object DetectionCode2
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and TrackingCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object DetectionCode2
DiffBEV: Conditional Diffusion Model for Bird's Eye View PerceptionCode2
V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative PerceptionCode2
Show:102550
← PrevPage 2 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