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 826–850 of 1576 papers

TitleStatusHype
BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving ScenariosCode1
Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection—0
Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection—0
SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection—0
Towards Accurate Ground Plane Normal Estimation from Ego-MotionCode1
SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point CloudCode1
DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection—0
3D Object Aided Self-Supervised Monocular Depth Estimation—0
IDMS: Instance Depth for Multi-scale Monocular 3D Object Detection—0
BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks—0
MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object DetectionCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object DetectionCode0
BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection—0
Superpoint Transformer for 3D Scene Instance SegmentationCode1
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection TransformersCode1
3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object DetectionCode1
Sparse2Dense: Learning to Densify 3D Features for 3D Object DetectionCode1
UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes—0
Transformation-Equivariant 3D Object Detection for Autonomous Driving—0
AeDet: Azimuth-invariant Multi-view 3D Object DetectionCode1
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world LearningCode2
Context-Aware Data Augmentation for LIDAR 3D Object Detection—0
Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal FusionCode2
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective SupervisionCode4
Show:102550
← PrevPage 34 of 64Next →
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