No article text was recorded for this version.
3D annotation bottleneck (LiDAR labeling cost)
Version 1 of 159 papers60 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
- Blog: Reflective Teacher: Semi-Supervised Multimodal 3D Object Detection in Bird's-Eye-View via Uncertainty Measure
- Blog: Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection
- Blog: Towards Unsupervised Object Detection from LiDAR Point Clouds
- Blog: Kecor: Kernel Coding Rate Maximization for Active 3D Object Detection
- Blog: Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection
- Blog: DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
- Blog: OpenBox: Annotate Any Bounding Boxes in 3D
- Blog: CSOT: Cross-scan Object Transfer for Semi-Supervised LiDAR Object Detection
- Blog: FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
- Blog: Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection
- Blog: Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling
- Blog: Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection
- Blog: MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency
- Blog: Context-Aware Data Augmentation for LIDAR 3d Object Detection
- Blog: SCP: SCENE COMPLETION PRE-TRAINING FOR 3D OBJECT DETECTION
- Blog: One Million Scenes for Autonomous Driving: ONCE Dataset
- Blog: TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
- Blog: Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation
- Blog: Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels
- Blog: Three Pillars Improving Vision Foundation Model Distillation for Lidar
- Blog: ST3D: Self-Training for Unsupervised Domain Adaptation on 3D Object Detection
- Blog: Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
- Blog: CoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework
- Blog: PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector
- Blog: Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection
- Blog: MonoSOWA: Scalable Monocular 3D Object Detector Without Human Annotations
- Blog: Motal: Unsupervised 3D Object Detection by Modality and Task-specific Knowledge Transfer
- Blog: Semi-supervised Monocular 3D Object Detection by Multi-view Consistency
- Blog: BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios
- Blog: UNIT: Unsupervised Online Instance Segmentation through Time
- Blog: SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts
- Blog: Semi-supervised 3D Object Detection via Temporal Graph Neural Networks
- Blog: Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
- Blog: SESS: Self-Ensembling Semi-Supervised 3D Object Detection
- Blog: Correction: CMAE-3D: Contrastive Masked AutoEncoders for Self-Supervised 3D Object Detection
- Blog: Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos
- Blog: UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
- Blog: SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
- Blog: Loss Function Optimization Method and Unsupervised Extraction Approach D-DBSCAN for Improving the Moving Target Perception of 3D Imaging Sonar
- Blog: Unsupervised Subcategory Domain Adaptive Network for 3D Object Detection in LiDAR
- Blog: TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection
- Blog: A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection
- Blog: Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection
- Blog: WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
- Blog: Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection
- Blog: MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
- Blog: 3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
- Blog: MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection
- Blog: High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning
- Blog: Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection
- Blog: VLM2Scene: Self-Supervised Image-Text-LiDAR Learning with Foundation Models for Autonomous Driving Scene Understanding
- Blog: Refining the ONCE Benchmark With Hyperparameter Tuning
- Blog: Semi-supervised 3D Object Detection with Proficient Teachers
- Blog: What My Motion tells me about Your Pose: A Self-Supervised Monocular 3D Vehicle Detector
- Blog: ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
- Blog: Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
- Blog: ZeroFlow: Scalable Scene Flow via Distillation
- Blog: Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector
History & citation
Current · Permanent link
- Efficient 3D Object Detection via Label Minimization merged into this direction (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_3d_annotation_bottleneck_lidar_labeling__07239326,
title = {3D annotation bottleneck (LiDAR labeling cost)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/3d-annotation-bottleneck-lidar-labeling-cost/rdr_0723932601814613adeef4ade608bbc5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_3d_annotation_bottleneck_lidar_labeling__07239326_v1,
title = {3D annotation bottleneck (LiDAR labeling cost)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/3d-annotation-bottleneck-lidar-labeling-cost/rdr_0723932601814613adeef4ade608bbc5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}