Masked Surfel Prediction for Self-Supervised Point Cloud Learning

07/07/2022
by   Yabin Zhang, et al.
8

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry information, which is also important to understand the point cloud data. In this work, we make the first attempt, to the best of our knowledge, to consider the local geometry information explicitly into the masked auto-encoding, and propose a novel Masked Surfel Prediction (MaskSurf) method. Specifically, given the input point cloud masked at a high ratio, we learn a transformer-based encoder-decoder network to estimate the underlying masked surfels by simultaneously predicting the surfel positions (i.e., points) and per-surfel orientations (i.e., normals). The predictions of points and normals are supervised by the Chamfer Distance and a newly introduced Position-Indexed Normal Distance in a set-to-set manner. Our MaskSurf is validated on six downstream tasks under three fine-tuning strategies. In particular, MaskSurf outperforms its closest competitor, Point-MAE, by 1.2% on the real-world dataset of ScanObjectNN under the OBJ-BG setting, justifying the advantages of masked surfel prediction over masked point cloud reconstruction. Codes will be available at https://github.com/YBZh/MaskSurf.

READ FULL TEXT

page 3

page 8

page 11

page 12

research
11/13/2022

Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning

Masked autoencoder has demonstrated its effectiveness in self-supervised...
research
12/08/2021

Garment4D: Garment Reconstruction from Point Cloud Sequences

Learning to reconstruct 3D garments is important for dressing 3D human b...
research
05/22/2023

Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning

We present a new self-supervised paradigm on point cloud sequence unders...
research
01/20/2022

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

Self-supervised learning has not been fully explored for point cloud ana...
research
08/10/2023

SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data

This paper proposes a new method to infer keypoints from arbitrary objec...
research
03/23/2023

PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds

Self-supervised learning is attracting large attention in point cloud un...
research
04/16/2023

PCPNet: An Efficient and Semantic-Enhanced Transformer Network for Point Cloud Prediction

The ability to predict future structure features of environments based o...

Please sign up or login with your details

Forgot password? Click here to reset