Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning
- 2 October 2026
- book chapter
- Published by Springer Nature
- p. 248-265
Abstract
No abstract availableKeywords
This publication has 36 references indexed in Scilit:
- DCMAE: A dual-branch contrastive masked autoencoder for 3D object detectionJournal of Visual Communication and Image Representation, 2025
- Multi-modal Relation Distillation for Unified 3D Representation Learning2024
- Depth Contrast: Self-supervised Pretraining on 3DPM Images for Mining Material Classification2023
- Masked Autoencoders for Point Cloud Self-supervised Learning2022
- Masked Discrimination for Self-supervised Learning on Point Clouds2022
- PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding2020
- PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation2020
- DGCNN: A convolutional neural network over large-scale labeled graphsNeural Networks, 2018
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- 3D ShapeNets: A deep representation for volumetric shapes2015