Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
Yong-Qiang Mao, Hanbo Bi, Xuexue Li, Kaiqiang Chen, Zhirui Wang, Xian Sun, Kun Fu
得益于深度学习技术在遥感领域点云处理中的应用，点云分割近年来已成为研究热点，可应用于真实三维场景、智慧城市等领域。尽管现有方法已取得前所未有的进展，但它们忽视了遥感领域点云按照纬度、经度和高度严格排列的固有特征，而这一特征为遥感领域的点云分割带来了极大便利。为巧妙利用这一特性，我们提出了名为孪生可变形点卷积（Twin Deformable point Convolutions，TDConvs）的新型卷积算子，旨在通过分别在经纬平面和高度方向上学习可变形采样点来实现自适应特征学习。首先，为建模经纬平面的特征，我们提出了柱形可变形点卷积（Cylinder-wise Deformable point Convolution，CyDConv）算子，该算子通过在经纬方向构建类柱体网格来生成二维柱体图。此外，为更好地融合经纬平面特征与空间几何特征，我们对提取的经纬特征和空间几何特征进行多尺度融合，并通过聚合不同尺度的相邻点特征来实现。另外，我们引入了球形可变形点卷积（Sphere-wise Deformable point Convolution，SpDConv）算子，通过构建球体网格结构来自适应地偏移三维空间中的采样点，旨在建模高度方向上的特征。在现有流行基准上的实验表明，我们的 TDConvs 取得了最佳分割性能，超越了现有的最先进方法。
英文摘要：
Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud segmentation has become a research hotspot in recent years, which can be applied to real-world 3D, smart cities, and other fields. Although existing solutions have made unprecedented progress, they ignore the inherent characteristics of point clouds in remote sensing fields that are strictly arranged according to latitude, longitude, and altitude, which brings great convenience to the segmentation of point clouds in remote sensing fields. To consider this property cleverly, we propose novel convolution operators, termed Twin Deformable point Convolutions (TDConvs), which aim to achieve adaptive feature learning by learning deformable sampling points in the latitude-longitude plane and altitude direction, respectively. First, to model the characteristics of the latitude-longitude plane, we propose a Cylinder-wise Deformable point Convolution (CyDConv) operator, which generates a two-dimensional cylinder map by constructing a cylinder-like grid in the latitude-longitude direction. Furthermore, to better integrate the features of the latitude-longitude plane and the spatial geometric features, we perform a multi-scale fusion of the extracted latitude-longitude features and spatial geometric features, and realize it through the aggregation of adjacent point features of different scales. In addition, a Sphere-wise Deformable point Convolution (SpDConv) operator is introduced to adaptively offset the sampling points in three-dimensional space by constructing a sphere grid structure, aiming at modeling the characteristics in the altitude direction. Experiments on existing popular benchmarks conclude that our TDConvs achieve the best segmentation performance, surpassing the existing state-of-the-art methods.
DC-Mamba: Bi-temporal deformable alignment and scale-sparse enhancement for remote sensing change detection
Min Sun School of Materials Science and Engineering Hainan University（孙敏 海南大学材料科学与工程学院）；Fenghui Guo School of Materials Science and Engineering Hainan University（郭峰 海南大学材料科学与工程学院）
In the field of Earth Observation (EO), Continual Learning (CL) algorithms have been proposed to deal with large datasets by decomposing them into several subsets and processing them incrementally. The majority of these algorithms assume that data is (a) coming from a single source, and (b) fully labeled. Real-world EO datasets are instead characterized by a large heterogeneity (e.g., coming from aerial, satellite, or drone scenarios), and for the most part they are unlabeled, meaning they can be fully exploited only through the emerging Self-Supervised Learning (SSL) paradigm. For these reaso…
SDL-MVS: View Space and Depth Deformable Learning Paradigm for Multi-View Stereo Reconstruction in Remote Sensing
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
Digital Twin Driven Textile Classification and Foreign Object Recognition in Automated Sorting Systems
Institute of Smart Systems Technologies（智能系统技术研究所）；University of Klagenfurt（克雷格弗特大学）；AAU SAL USE Laboratory（AAU SAL USE实验室）；Silicon Austria Labs（硅 Austria 实验室）
MaskCD: A Remote Sensing Change Detection Network Based on Mask Classification
Helmholtz Institute Freiberg for Resource Technology（弗莱贝格亥姆霍兹资源技术研究所）；Helmholtz-Zentrum Dresden-Rossendorf（德累斯顿-罗森多夫亥姆霍兹中心）；Technical University of Munich (TUM)（慕尼黑工业大学）；School of Information Science and Engineering, Wuhan University of Science and Technology（武汉科技大学信息科学与工程学院）；School of Engineering, Shiv Nadar University（希夫·纳达尔大学工程学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Lancaster University（兰卡斯特大学）
Modeling forests using historical data allows for more accurately evolution analysis, thus providing an important basis for other studies. As a recognized and effective tool, remote sensing plays an important role in forestry analysis. We can use it to derive information about the forest, including tree type, coverage and canopy density. There are many forest time series modeling studies using statistic values, but few using remote sensing images. Image prediction digital twin is an implementation of digital twin, which aims to predict future images bases on historical data. In this paper, we …
UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images
School of Computer Technology and Applications, Qinghai University（青海大学计算机技术与应用学院）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Estimating accurate number of interested objects from a given image is a challenging yet important task. Significant efforts have been made to address this problem and achieve great progress, yet counting number of ground objects from remote sensing images is barely studied. In this paper, we are interested in counting dense objects from remote sensing images. Compared with object counting in natural scene, this task is challenging in following factors: large scale variation, complex cluttered background and orientation arbitrariness. More importantly, the scarcity of data severely limits the …
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Object counting, whose aim is to estimate the number of objects from a given image, is an important and challenging computation task. Significant efforts have been devoted to addressing this problem and achieved great progress, yet counting the number of ground objects from remote sensing images is barely studied. In this paper, we are interested in counting dense objects from remote sensing images. Compared with object counting in a natural scene, this task is challenging in the following factors: large scale variation, complex cluttered background, and orientation arbitrariness. More importa…
DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation
Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）；National University of Singapore（新加坡国立大学）；Technical University of Munich（慕尼黑工业大学）；NVIDIA（英伟达）
