English
Related papers

Related papers: FILTR: Extracting Topological Features from Pretra…

200 papers

Large-scale 3D point clouds (LS3DPC) obtained by LiDAR scanners require huge storage space and transmission bandwidth due to a large amount of data. The existing methods of LS3DPC compression separately perform rule-based point sampling and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Jae-Young Yim , Jae-Young Sim

In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this…

Machine Learning · Computer Science 2016-06-07 Bert De Brabandere , Xu Jia , Tinne Tuytelaars , Luc Van Gool

A fundamental question in learning to classify 3D shapes is how to treat the data in a way that would allow us to construct efficient and accurate geometric processing and analysis procedures. Here, we restrict ourselves to networks that…

Computational Geometry · Computer Science 2019-10-04 Mor Joseph-Rivlin , Alon Zvirin , Ron Kimmel

The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training data of 3D point cloud is limited. To overcome this…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Yuan Yao , Yuanhan Zhang , Zhenfei Yin , Jiebo Luo , Wanli Ouyang , Xiaoshui Huang

To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…

Computer Vision and Pattern Recognition · Computer Science 2022-11-21 Xiang Li , Mingyang Wang , Congcong Wen , Lingjing Wang , Nan Zhou , Yi Fang

3D object classification is a crucial problem due to its significant practical relevance in many fields, including computer vision, robotics, and autonomous driving. Although deep learning methods applied to point clouds sampled on CAD…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Anirban Ghosh , Ayan Dutta

Deep-learning models can extract a rich assortment of features from data. Which features a model uses depends not only on \emph{predictivity} -- how reliably a feature indicates training-set labels -- but also on \emph{availability} -- how…

Machine Learning · Computer Science 2024-07-15 Katherine L. Hermann , Hossein Mobahi , Thomas Fel , Michael C. Mozer

Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and…

Machine Learning · Computer Science 2022-11-16 Zuoyu Yan , Tengfei Ma , Liangcai Gao , Zhi Tang , Yusu Wang , Chao Chen

Deep convolutional neural networks have led to breakthrough results in practical feature extraction applications. The mathematical analysis of these networks was pioneered by Mallat, 2012. Specifically, Mallat considered so-called…

Machine Learning · Computer Science 2016-09-05 Thomas Wiatowski , Helmut Bölcskei

Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by…

Image and Video Processing · Electrical Eng. & Systems 2021-10-12 Ali Hatamizadeh , Yucheng Tang , Vishwesh Nath , Dong Yang , Andriy Myronenko , Bennett Landman , Holger Roth , Daguang Xu

This study proposes an automated data mining framework based on autoencoders and experimentally verifies its effectiveness in feature extraction and data dimensionality reduction. Through the encoding-decoding structure, the autoencoder can…

Machine Learning · Computer Science 2024-12-04 Yaxin Liang , Xinshi Li , Xin Huang , Ziqi Zhang , Yue Yao

Line clouds, though under-investigated in the previous work, potentially encode more compact structural information of buildings than point clouds extracted from multi-view images. In this work, we propose the first network to process line…

Computer Vision and Pattern Recognition · Computer Science 2022-11-07 Yicheng Luo , Jing Ren , Xuefei Zhe , Di Kang , Yajing Xu , Peter Wonka , Linchao Bao

Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Xuran Pan , Zhuofan Xia , Shiji Song , Li Erran Li , Gao Huang

Neural signed distance functions (SDFs) have shown powerful ability in fitting the shape geometry. However, inferring continuous signed distance fields from discrete unoriented point clouds still remains a challenge. The neural network…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Shengtao Li , Ge Gao , Yudong Liu , Ming Gu , Yu-Shen Liu

We present a new deep learning approach for matching deformable shapes by introducing {\it Shape Deformation Networks} which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a…

Computer Vision and Pattern Recognition · Computer Science 2018-07-30 Thibault Groueix , Matthew Fisher , Vladimir G. Kim , Bryan C. Russell , Mathieu Aubry

While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering…

Machine Learning · Computer Science 2024-11-06 Kun Yi , Jingru Fei , Qi Zhang , Hui He , Shufeng Hao , Defu Lian , Wei Fan

We present an approach to inform the reconstruction of a surface from a point scan through topological priors. The reconstruction is based on basis functions which are optimized to provide a good fit to the point scan while satisfying…

Computational Geometry · Computer Science 2021-09-17 Rickard Brüel-Gabrielsson , Vignesh Ganapathi-Subramanian , Primoz Skraba , Leonidas J. Guibas

This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a…

Computer Vision and Pattern Recognition · Computer Science 2015-02-26 Adam W. Harley , Alex Ufkes , Konstantinos G. Derpanis

Persistence diagrams play a fundamental role in Topological Data Analysis where they are used as topological descriptors of filtrations built on top of data. They consist in discrete multisets of points in the plane $\mathbb{R}^2$ that can…

Computational Geometry · Computer Science 2019-03-25 Frédéric Chazal , Vincent Divol

Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-29 Yonglin Tian , Lichao Huang , Xuesong Li , Kunfeng Wang , Zilei Wang , Fei-Yue Wang