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 121–130 of 1576 papers

TitleStatusHype
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
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
Unifying Voxel-based Representation with Transformer for 3D Object DetectionCode2
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
BEVFusion: A Simple and Robust LiDAR-Camera Fusion FrameworkCode2
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous DrivingCode2
PillarNet: Real-Time and High-Performance Pillar-based 3D Object DetectionCode2
Show:102550
← PrevPage 13 of 158Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EA-LSSNDS0.78—Unverified
2MegFusionNDS0.77—Unverified
3MMFusion-eNDS0.77—Unverified
4DeepInteraction-largeNDS0.76—Unverified
5DeepInteraction-eNDS0.76—Unverified
6BEVFusion-eNDS0.76—Unverified
7RacoonPowerNDS0.76—Unverified
8ADS-TEAMNDS0.75—Unverified
9CenterPoint-FusionNDS0.75—Unverified
10UniTRNDS0.75—Unverified