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 251–300 of 1576 papers

TitleStatusHype
LION: Linear Group RNN for 3D Object Detection in Point CloudsCode3
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels OnlyCode1
DVPE: Divided View Position Embedding for Multi-View 3D Object DetectionCode0
What Matters in Range View 3D Object DetectionCode1
MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object DetectionCode2
Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object DetectionCode0
Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object DetectionCode1
RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies—0
General Geometry-aware Weakly Supervised 3D Object DetectionCode1
ParCon: Noise-Robust Collaborative Perception via Multi-module Parallel Connection—0
OPEN: Object-wise Position Embedding for Multi-view 3D Object DetectionCode2
RepVF: A Unified Vector Fields Representation for Multi-task 3D PerceptionCode1
LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object DetectionCode1
Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape DataCode0
FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object DetectionCode1
When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark DatasetCode2
Semi-supervised 3D Object Detection with PatchTeacher and PillarMixCode0
Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D SceneCode1
FYI: Flip Your Images for Dataset Distillation—0
Exploring Camera Encoder Designs for Autonomous Driving Perception—0
Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework—0
Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image—0
Towards Stable 3D Object Detection—0
Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object DetectionCode0
DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection—0
BiCo-Fusion: Bidirectional Complementary LiDAR-Camera Fusion for Semantic- and Spatial-Aware 3D Object Detection—0
STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning—0
CTS: Sim-to-Real Unsupervised Domain Adaptation on 3D Detection—0
Towards Open-set Camera 3D Object Detection—0
MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object DetectionCode0
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object DetectionCode1
DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object DetectionCode0
Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint—0
Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object DetectionCode0
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding—0
Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object DetectionCode0
SparseDet: A Simple and Effective Framework for Fully Sparse LiDAR-based 3D Object Detection—0
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object DetectionCode2
EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation ModelsCode2
Shelf-Supervised Cross-Modal Pre-Training for 3D Object DetectionCode0
BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object DetectionCode2
CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise TransformerCode0
Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D SensingCode0
EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy NetworkCode2
RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks—0
UCDNet: Multi-UAV Collaborative 3D Object Detection Network by Reliable Feature Mapping—0
UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection—0
Multi-Object Tracking based on Imaging Radar 3D Object Detection—0
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision TransformerCode2
Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object DetectionCode3
Show:102550
← PrevPage 6 of 32Next →
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
2MegFusionNDS0.77—Unverified
3MMFusion-eNDS0.77—Unverified
4BEVFusion-eNDS0.76—Unverified
5RacoonPowerNDS0.76—Unverified
6DeepInteraction-largeNDS0.76—Unverified
7DeepInteraction-eNDS0.76—Unverified
8FusionVPENDS0.75—Unverified
9FocalFormer3D-FNDS0.75—Unverified
10CenterPoint-FusionNDS0.75—Unverified