Point Clouds Meets Physics: Dynamic Acoustic Field Fitting Network for Point Cloud Understanding

While existing pre-training-based methods have enhanced point cloud model performance, they have not fundamentally resolved the challenge of local structure representation in point clouds. The limited representational capacity of pure point cloud models continues to constrain the potential of cross-...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) p. 22182
Main Authors: Wang, Changshuo, He, Shuting, Fang, Xiang, Han, Jiawei, Liu, Zhonghang, Ning, Xin, Li, Weijun, Tiwari, Prayag
Format: Conference Proceeding
Language:English
Published: IEEE 10.06.2025
Series:IEEE Conference on Computer Vision and Pattern Recognition. Proceedings
Subjects:
Acoustic field
Adaptation models
Computer architecture
Convolution
Fitting
Pattern recognition
Point cloud compression
Shape
Solid modeling
Three-dimensional displays
ISBN:9798331543648, 9798331543655
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:While existing pre-training-based methods have enhanced point cloud model performance, they have not fundamentally resolved the challenge of local structure representation in point clouds. The limited representational capacity of pure point cloud models continues to constrain the potential of cross-modal fusion methods and performance across various tasks. To address this challenge, we propose a Dynamic Acoustic Field Fitting Network (DAF-Net), inspired by physical acoustic principles. Specifically, we represent local point clouds as acoustic fields and introduce a novel Acoustic Field Convolution (AF-Conv), which treats local aggregation as an acoustic energy field modeling problem and captures fine-grained local shape awareness by dividing the local area into near field and far field. Furthermore, drawing inspiration from multi-frequency wave phenomena and dynamic convolution, we develop the Dynamic Acoustic Field Convolution (DAF-Conv) based on AF-Conv. DAF-Conv dynamically generates multiple weights based on local geometric priors, effectively enhancing adaptability to diverse geometric features. Additionally, we design a Global Shape-Aware (GSA) layer incorporating EdgeConv and multi-head attention mechanisms, which combines with DAF-Conv to form the DAF Block. These blocks are then stacked to create a hierarchical DAFNet architecture. Extensive experiments demonstrate that DAFNet significantly outperforms existing methods across multiple tasks.
ISBN:9798331543648
9798331543655
ISSN:1063-6919
DOI:10.1109/CVPR52734.2025.02066