Saved in:
Bibliographic Details
Main Authors: Hu, Barry Shichen, Liang, Siyun, Paetzold, Johannes, Nguyen, Huy H., Echizen, Isao, Tang, Jiapeng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.05745
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917563893547008
author Hu, Barry Shichen
Liang, Siyun
Paetzold, Johannes
Nguyen, Huy H.
Echizen, Isao
Tang, Jiapeng
author_facet Hu, Barry Shichen
Liang, Siyun
Paetzold, Johannes
Nguyen, Huy H.
Echizen, Isao
Tang, Jiapeng
contents We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input scales, then focus on a surface fitting method by which local point cloud neighborhoods are fitted to a geometric surface approximated by either a polynomial function or a multi-layer perceptron (MLP). However, fitting surfaces to fixed-order polynomial functions can suffer from overfitting or underfitting, and learning MLP-represented hyper-surfaces requires pre-generated per-point weights. To avoid these limitations, we first unify the design choices in previous works and then propose a simplified Transformer-based model to extract richer and more robust geometric features for the surface normal estimation task. Through extensive experiments, we demonstrate that our Transformer-based method achieves state-of-the-art performance on both the synthetic shape dataset PCPNet, and the real-world indoor scene dataset SceneNN, exhibiting more noise-resilient behavior and significantly faster inference. Most importantly, we demonstrate that the sophisticated hand-designed modules in existing works are not necessary to excel at the task of surface normal estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05745
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Surface Normal Estimation with Transformers
Hu, Barry Shichen
Liang, Siyun
Paetzold, Johannes
Nguyen, Huy H.
Echizen, Isao
Tang, Jiapeng
Computer Vision and Pattern Recognition
We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input scales, then focus on a surface fitting method by which local point cloud neighborhoods are fitted to a geometric surface approximated by either a polynomial function or a multi-layer perceptron (MLP). However, fitting surfaces to fixed-order polynomial functions can suffer from overfitting or underfitting, and learning MLP-represented hyper-surfaces requires pre-generated per-point weights. To avoid these limitations, we first unify the design choices in previous works and then propose a simplified Transformer-based model to extract richer and more robust geometric features for the surface normal estimation task. Through extensive experiments, we demonstrate that our Transformer-based method achieves state-of-the-art performance on both the synthetic shape dataset PCPNet, and the real-world indoor scene dataset SceneNN, exhibiting more noise-resilient behavior and significantly faster inference. Most importantly, we demonstrate that the sophisticated hand-designed modules in existing works are not necessary to excel at the task of surface normal estimation.
title Surface Normal Estimation with Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.05745