Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling

Wijaya, Kevin Tirta; Paek, Dong-Hee; Kong, Seung-Hyun

doi:10.48550/arxiv.2205.09962

Cited by 4 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 A simplified architecture of PointNet [3] where parameters n and m denote point number and feature dimension, respectively arable MLPs and an inverted residual bottleneck design to PointNet++ to facilitate effective and efficient model scaling. In PointStack [106], the authors proposed a method that utilizes multi-resolution features and learnable pooling to extract meaningful features from point cloud data. The multi-resolution features capture the underlying structure of the point cloud data at different scales, while the learnable pooling enables the system to dynamically adjust the pooling operation based on the features.…”

Section: Multi-layer Perceptron (Mlp) Methodsmentioning

confidence: 99%

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Sarker,

Stone

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-namely, 3D shape classification and semantic segmentation.

show abstract

Section: Multi-layer Perceptron (Mlp) Methodsmentioning

confidence: 99%

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Sarker,

Stone

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Inspired by CNN, PointNet++ [12] is proposed, which is able to extract local features at different scales and obtain deep features via a multi-layer network structure. In a recent study, Wijaya et al proposed a new PointNet-based point cloud feature learning network: PointStack [15]. It features multi-resolution feature learning and learnable pooling, which further reduces the information loss during sampling.…”

Section: Traditional Point Cloud Learning Methodsmentioning

confidence: 99%

RST: Rough Set Transformer for Point Cloud Learning

Sun,

Zeng

2023

Sensors

View full text Add to dashboard Cite

Point cloud data generated by LiDAR sensors play a critical role in 3D sensing systems, with applications encompassing object classification, part segmentation, and point cloud recognition. Leveraging the global learning capacity of dot product attention, transformers have recently exhibited outstanding performance in point cloud learning tasks. Nevertheless, existing transformer models inadequately address the challenges posed by uncertainty features in point clouds, which can introduce errors in the dot product attention mechanism. In response to this, our study introduces a novel global guidance approach to tolerate uncertainty and provide a more reliable guidance. We redefine the granulation and lower-approximation operators based on neighborhood rough set theory. Furthermore, we introduce a rough set-based attention mechanism tailored for point cloud data and present the rough set transformer (RST) network. Our approach utilizes granulation concepts derived from token clusters, enabling us to explore relationships between concepts from an approximation perspective, rather than relying on specific dot product functions. Empirically, our work represents the pioneering fusion of rough set theory and transformer networks for point cloud learning. Our experimental results, including point cloud classification and segmentation tasks, demonstrate the superior performance of our method. Our method establishes concepts based on granulation generated from clusters of tokens. Subsequently, relationships between concepts can be explored from an approximation perspective, instead of relying on specific dot product or addition functions. Empirically, our work represents the pioneering fusion of rough set theory and transformer networks for point cloud learning. Our experimental results, including point cloud classification and segmentation tasks, demonstrate the superior performance of our method.

show abstract

“…These costs may increase prohibitively in the case of large-scale point clouds with a large number of points and deep networks. Unlike the abovementioned methods, point-based methods [6], [19], [20], [21] directly use raw point clouds without any preprocessing steps. The absolute position of points in terms of x, y, and z coordinates is used as the input data.…”

Section: A Point-cloud Deep Learning Methodsmentioning

confidence: 99%

PMHA-Net: Positional Multi-Head Attention Network for Point-Cloud Part Segmentation and Classification

Jeon,

Hong,

Lee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

For understanding unordered sets of point clouds, the positional information of each point must be effectively used. To this end, the existing models use the absolute position of the point and its relative position within a local group. However, accurately capturing the positional information is challenging because the relative position within a local group typically has a considerably smaller value than that of the feature information. Moreover, in terms of the data characteristics of point clouds, closer points are more strongly correlated, but their relative position approaches zero. To address these problems, we process the relative position within a local group by normalizing it within the overall object range and local range according to the data characteristics. This transformation helps maintain the meaning and pattern of the relative position while facilitating its learning. The transformed data are combined with the absolute position to encode the position vector, which serves as the positional encoding in multi-head attention across multiple resolutions. Extensive experiments are conducted on benchmark point cloud datasets to demonstrate that the proposed model exhibits competitive performance in part segmentation and classification tasks.

show abstract

Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling

Cited by 4 publications

References 0 publications

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

RST: Rough Set Transformer for Point Cloud Learning

PMHA-Net: Positional Multi-Head Attention Network for Point-Cloud Part Segmentation and Classification

Contact Info

Product

Resources

About