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 641650 of 1576 papers

TitleStatusHype
SAM3D: Zero-Shot 3D Object Detection via Segment Anything ModelCode2
OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection0
CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception0
Doubly Robust Self-TrainingCode0
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color ContrastCode1
UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous DrivingCode2
VCVW-3D: A Virtual Construction Vehicles and Workers Dataset with 3D AnnotationsCode0
Monocular 2D Camera-based Proximity Monitoring for Human-Machine Collision Warning on Construction SitesCode0
View-to-Label: Multi-View Consistency for Self-Supervised 3D Object Detection0
Radar Enlighten the Dark: Enhancing Low-Visibility Perception for Automated Vehicles with Camera-Radar FusionCode1
Show:102550
← PrevPage 65 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