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 110 of 1576 papers

TitleStatusHype
Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis0
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR RepresentationsCode1
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object DetectionCode2
A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects0
Vision-based Lifting of 2D Object Detections for Automated Driving0
Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds0
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos0
Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting0
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation ModelsCode3
SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding0
Show:102550
← PrevPage 1 of 158Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MonoUNIAP|R40(moderate)87.2Unverified
2CoBEVAP|R40(moderate)69.6Unverified
3BEVHeightAP|R40(moderate)65.8Unverified
4BEVDepthAP|R40(moderate)63.6Unverified
5CBRAP|R40(moderate)60.1Unverified
6PointPillarsAP|R40(moderate)54Unverified
7MVXNetAP|R40(moderate)53.7Unverified
8BEVFormerAP|R40(moderate)50.7Unverified
9ImVoxelNetAP|R40(moderate)37.6Unverified