DeepAI AI Chat
Log In Sign Up

DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion

11/19/2021
by   Renrui Zhang, et al.
University of Pennsylvania
ShanghaiTech University
0

Point cloud processing is a challenging task due to its sparsity and irregularity. Prior works introduce delicate designs on either local feature aggregator or global geometric architecture, but few combine both advantages. We propose Dual-Scale Point Cloud Recognition with High-frequency Fusion (DSPoint) to extract local-global features by concurrently operating on voxels and points. We reverse the conventional design of applying convolution on voxels and attention to points. Specifically, we disentangle point features through channel dimension for dual-scale processing: one by point-wise convolution for fine-grained geometry parsing, the other by voxel-wise global attention for long-range structural exploration. We design a co-attention fusion module for feature alignment to blend local-global modalities, which conducts inter-scale cross-modality interaction by communicating high-frequency coordinates information. Experiments and ablations on widely-adopted ModelNet40, ShapeNet, and S3DIS demonstrate the state-of-the-art performance of our DSPoint.

READ FULL TEXT
06/27/2022

Multi-scale Network with Attentional Multi-resolution Fusion for Point Cloud Semantic Segmentation

In this paper, we present a comprehensive point cloud semantic segmentat...
03/18/2023

3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process

We develop a generalized 3D shape generation prior model, tailored for m...
03/31/2022

Cross-modal Learning of Graph Representations using Radar Point Cloud for Long-Range Gesture Recognition

Gesture recognition is one of the most intuitive ways of interaction and...
08/20/2021

Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis

Convolutional neural network has made remarkable achievements in classif...
11/26/2022

CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion

Multi-modality (MM) image fusion aims to render fused images that mainta...
07/04/2022

Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

Modeling the local surface geometry is challenging in 3D point cloud und...
04/27/2021

Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation

Self-attention mechanism recently achieves impressive advancement in Nat...