Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Bangzhen, Zheng, Chenxi, Xu, Xuemiao, Xu, Cheng, Zhang, Huaidong, He, Shengfeng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913677956874240
author Liu, Bangzhen
Zheng, Chenxi
Xu, Xuemiao
Xu, Cheng
Zhang, Huaidong
He, Shengfeng
author_facet Liu, Bangzhen
Zheng, Chenxi
Xu, Xuemiao
Xu, Cheng
Zhang, Huaidong
He, Shengfeng
contents The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02247
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning
Liu, Bangzhen
Zheng, Chenxi
Xu, Xuemiao
Xu, Cheng
Zhang, Huaidong
He, Shengfeng
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
I.2.10
The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization.
title Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
I.2.10
url https://arxiv.org/abs/2502.02247