Pith. sign in

REVIEW 6 cited by

Masked Autoencoders for Point Cloud Self-supervised Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.06604 v2 pith:BWHT4AHY submitted 2022-03-13 cs.CV

Yatian Pang , Wenxiao Wang , Francis E.H. Tay , Wei Liu , Yonghong Tian , Li Yuan This is my paper · ORCID
classification cs.CV
keywords pointcloudlearningmaskedself-supervisedpatchesschemeaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud self-supervised learning, addressing the challenges posed by point cloud's properties, including leakage of location information and uneven information density. Concretely, we divide the input point cloud into irregular point patches and randomly mask them at a high ratio. Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches. Extensive experiments show that our approach is efficient during pre-training and generalizes well on various downstream tasks. Specifically, our pre-trained models achieve 85.18% accuracy on ScanObjectNN and 94.04% accuracy on ModelNet40, outperforming all the other self-supervised learning methods. We show with our scheme, a simple architecture entirely based on standard Transformers can surpass dedicated Transformer models from supervised learning. Our approach also advances state-of-the-art accuracies by 1.5%-2.3% in the few-shot object classification. Furthermore, our work inspires the feasibility of applying unified architectures from languages and images to the point cloud.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The TIME Machine: On The Power of Motion for Efficient Perception

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    TIME is a motion-based embedding from point tracks, trained only on synthetic data via masked autoencoding, that matches state-of-the-art video model performance with up to 10,000x less training data.

  2. ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron Density

    cs.LG 2026-08 conditional novelty 6.0 of 10

    ED-DiT pretrains a diffusion transformer on electron-density point clouds with a physical electron-number constraint, and the resulting encoder outperforms scratch models across six molecular tasks.

  3. HEP-JEPA: A foundation model for collider physics using joint embedding predictive architecture

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A JEPA-style self-supervised transformer for collider jets improves few-shot classification and transfers to top and quark-gluon tagging, yet remains behind specialized taggers.

  4. Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding

    cs.CV 2025-01 conditional novelty 5.0 of 10

    Adding hierarchy-encouraging losses to hyperbolic text-image-point cloud contrastive training yields hierarchical 3D point cloud embeddings with small downstream gains.

  5. Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A 3D anomaly detection method that uses internal z-axis projection slices and Laplacian feature filtering reports state-of-the-art results on Real3D-AD and Anomaly-ShapeNet.

  6. ObitoNet: Multimodal High-Resolution Point Cloud Reconstruction

    cs.CV 2024-12 reject novelty 4.0 of 10

    ObitoNet fuses ViT image tokens and FPS/KNN point-cloud tokens with a cross-attention decoder, reporting a Chamfer loss of 1.36 on Tanks and Temples versus PointMAE's 1.53.

Pith tools