Hybrid Long and Short Range Flows for Point Cloud Filtering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Edirimuni, Dasith de Silva, Lu, Xuequan, Mian, Ajmal Saeed, Wei, Lei, Li, Gang, Schaefer, Scott, He, Ying
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909733702598656
author Edirimuni, Dasith de Silva
Lu, Xuequan
Mian, Ajmal Saeed
Wei, Lei
Li, Gang
Schaefer, Scott
He, Ying
author_facet Edirimuni, Dasith de Silva
Lu, Xuequan
Mian, Ajmal Saeed
Wei, Lei
Li, Gang
Schaefer, Scott
He, Ying
contents Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising. Recent filtering methods often suffer from point clustering or noise retaining issues. In this paper, we propose Hybrid Point Cloud Filtering ($\textbf{HybridPF}$) that considers both short-range and long-range filtering trajectories when removing noise. It is well established that short range scores, given by $\nabla_{x}\log p(x_t)$, may provide the necessary displacements to move noisy points to the underlying clean surface. By contrast, long range velocity flows approximate constant displacements directed from a high noise variant patch $x_0$ towards the corresponding clean surface $x_1$. Here, noisy patches $x_t$ are viewed as intermediate states between the high noise variant and the clean patches. Our intuition is that long range information from velocity flow models can guide the short range scores to align more closely with the clean points. In turn, score models generally provide a quicker convergence to the clean surface. Specifically, we devise two parallel modules, the ShortModule and LongModule, each consisting of an Encoder-Decoder pair to respectively account for short-range scores and long-range flows. We find that short-range scores, guided by long-range features, yield filtered point clouds with good point distributions and convergence near the clean surface. We design a joint loss function to simultaneously train the ShortModule and LongModule, in an end-to-end manner. Finally, we identify a key weakness in current displacement based methods, limitations on the decoder architecture, and propose a dynamic graph convolutional decoder to improve the inference process. Comprehensive experiments demonstrate that our HybridPF achieves state-of-the-art results while enabling faster inference speed.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08542
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Long and Short Range Flows for Point Cloud Filtering
Edirimuni, Dasith de Silva
Lu, Xuequan
Mian, Ajmal Saeed
Wei, Lei
Li, Gang
Schaefer, Scott
He, Ying
Graphics
Computer Vision and Pattern Recognition
Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising. Recent filtering methods often suffer from point clustering or noise retaining issues. In this paper, we propose Hybrid Point Cloud Filtering ($\textbf{HybridPF}$) that considers both short-range and long-range filtering trajectories when removing noise. It is well established that short range scores, given by $\nabla_{x}\log p(x_t)$, may provide the necessary displacements to move noisy points to the underlying clean surface. By contrast, long range velocity flows approximate constant displacements directed from a high noise variant patch $x_0$ towards the corresponding clean surface $x_1$. Here, noisy patches $x_t$ are viewed as intermediate states between the high noise variant and the clean patches. Our intuition is that long range information from velocity flow models can guide the short range scores to align more closely with the clean points. In turn, score models generally provide a quicker convergence to the clean surface. Specifically, we devise two parallel modules, the ShortModule and LongModule, each consisting of an Encoder-Decoder pair to respectively account for short-range scores and long-range flows. We find that short-range scores, guided by long-range features, yield filtered point clouds with good point distributions and convergence near the clean surface. We design a joint loss function to simultaneously train the ShortModule and LongModule, in an end-to-end manner. Finally, we identify a key weakness in current displacement based methods, limitations on the decoder architecture, and propose a dynamic graph convolutional decoder to improve the inference process. Comprehensive experiments demonstrate that our HybridPF achieves state-of-the-art results while enabling faster inference speed.
title Hybrid Long and Short Range Flows for Point Cloud Filtering
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.08542