No article text was recorded for this version.
label-efficient 3D learning
Version 1 of 146 papers47 conceptsfrozen 2026-10-04
Papers in this version
- Blog: SCP: SCENE COMPLETION PRE-TRAINING FOR 3D OBJECT DETECTION
- Blog: Ponder: Point Cloud Pre-training via Neural Rendering
- Blog: Towards foundational LiDAR world models with efficient latent flow matching
- Blog: Self-Supervised Pretraining for Large-Scale Point Clouds
- Blog: EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding
- Blog: FAC: 3D Representation Learning via Foreground Aware Feature Contrast
- Blog: FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
- Blog: Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
- Blog: Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving
- Blog: A Weakly Supervised Vehicle Detection Method from LiDAR Point Clouds
- Blog: Unified Medical Image Pre-training in Language-Guided Common Semantic Space
- Blog: GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds
- Blog: Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds
- Blog: Weakly Supervised Monocular 3D Object Detection Using Multi-View Projection and Direction Consistency
- Blog: Positional Contrastive Learning for Volumetric Medical Image Segmentation
- Blog: M33D: Learning 3D Priors Using Multi-Modal Masked Autoencoders for 2D Image and Video Understanding
- Blog: SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction
- Blog: AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
- Blog: Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point Clouds
- Blog: Contrastive Representation Learning for Hand Shape Estimation
- Blog: ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation
- Blog: FreePoint: Unsupervised Point Cloud Instance Segmentation
- Blog: MonoSOWA: Scalable Monocular 3D Object Detector Without Human Annotations
- Blog: Generalizable Local Feature Pre-training for Deformable Shape Analysis
- Blog: ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection
- Blog: Implicit Surface Contrastive Clustering for LiDAR Point Clouds
- Blog: BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios
- Blog: CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
- Blog: Progressive Multi-Modal Fusion for Robust 3D Object Detection
- Blog: PatchContrast: Self-Supervised Pre-Training for 3D Object Detection
- Blog: Correction: CMAE-3D: Contrastive Masked AutoEncoders for Self-Supervised 3D Object Detection
- Blog: Transfer Learning from Partial Annotations for Whole Brain Segmentation
- Blog: Self-Supervised Pre-Training with Masked Shape Prediction for 3D Scene Understanding
- Blog: CooPre: Cooperative Pretraining for V2X Cooperative Perception
- Blog: PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
- Blog: Unsupervised Pre-training Improves Tooth Segmentation in 3-Dimensional Intraoral Mesh Scans
- Blog: MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
- Blog: TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning
- Blog: Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos
- Blog: HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation
- Blog: Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection
- Blog: Neural Scene Decomposition for Multi-Person Motion Capture
- Blog: Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
- Blog: MBGRLp: Multiscale Bootstrap Graph Representation Learning on Pointcloud (Student Abstract)
- Blog: Unsupervised Contrastive Representation Learning for 3D Mesh Segmentation (Student Abstract)
- Blog: Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis
History & citation
Current · Permanent link
- This direction split from Label Efficient 3D Perception via Self Supervised Pretraining (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_label_efficient_3d_learning_e36405e7,
title = {label-efficient 3D learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/label-efficient-3d-learning/rdr_e36405e7d35f4aa5b3e5f24d0b4dfa3e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_label_efficient_3d_learning_e36405e7_v1,
title = {label-efficient 3D learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/label-efficient-3d-learning/rdr_e36405e7d35f4aa5b3e5f24d0b4dfa3e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}