Research map / Point clouds / Point cloud classification
Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training
Xiaoyang Xiao, Runzhao Yao, Zhiqiang Tian, Shaoyi Du
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Point-MaDi, a masked autoencoder for point cloud pre-training that combines masked reconstruction with a diffusion-based decoder, avoiding explicit positional embeddings that leak geometry.
Problem
Self-supervised pre-training for 3D point clouds is costly to annotate; masked autoencoders for point clouds rely on explicit positional embeddings such as patch center coordinates, which leak geometric information and limit data-driven structural learning.
Approach
Replaces explicit coordinate-based positional embeddings in masked point autoencoding with a diffusion-based generative formulation, so structure is learned from data rather than from leaked patch-center coordinates. Only the abstract was available, so details are limited.
Experimental setup
Builds on: masked autoencoders Point-MAE
Closest papers by meaning
- Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training (NeurIPS 2022 · similarity 0.93)
- Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders (AAAI 2024 · similarity 0.92)
- 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining (ICLR 2024 · similarity 0.91)
- PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders (NeurIPS 2024 · similarity 0.90)
- RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning (AAAI 2025 · similarity 0.90)
- Adaptive Siamese Masked Autoencoder with Global Optimization for Unsupervised Point Cloud Shape Correspondence (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
