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 6170 of 1576 papers

TitleStatusHype
BEVFusion: A Simple and Robust LiDAR-Camera Fusion FrameworkCode2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth EstimationCode2
EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation ModelsCode2
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object DetectionCode2
DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy PredictionCode2
3D Object Detection for Autonomous Driving: A Comprehensive SurveyCode2
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object DetectionCode2
DeepInteraction: 3D Object Detection via Modality InteractionCode2
Commonsense Prototype for Outdoor Unsupervised 3D Object DetectionCode2
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse TransformersCode2
Show:102550
← PrevPage 7 of 158Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EA-LSSNDS0.78Unverified
2MegFusionNDS0.77Unverified
3MMFusion-eNDS0.77Unverified
4BEVFusion-eNDS0.76Unverified
5RacoonPowerNDS0.76Unverified
6DeepInteraction-largeNDS0.76Unverified
7DeepInteraction-eNDS0.76Unverified
8FusionVPENDS0.75Unverified
9FocalFormer3D-FNDS0.75Unverified
10CenterPoint-FusionNDS0.75Unverified