Related papers: Curve Skeletonization in Continuous domain for Mes…
The automatic semantic segmentation of the huge amount of acquired remote sensing data has become an important task in the last decade. Images and Point Clouds (PCs) are fundamental data representations, particularly in urban mapping…
This paper focuses on the challenging task of learning 3D object surface reconstructions from single RGB images. Existing methods achieve varying degrees of success by using different geometric representations. However, they all have their…
A key scalability challenge in neural solvers for industrial-scale physics simulations is efficiently capturing both fine-grained local interactions and long-range global dependencies across millions of spatial elements. We introduce the…
We introduce a meshfree exterior calculus (MEEC) for learning structure-preserving descriptions of physics on point clouds, and use it to build MEEC-Net, a data-efficient surrogate that transfers across resolutions, geometries, and physical…
We propose a simple, data-efficient pipeline that augments an implicit reconstruction network based on neural SDF-based CAD parts with a part-segmentation head trained under PartField-generated supervision. Unlike methods tied to fixed…
In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…
Neural Controlled Differential Equations (Neural CDEs) provide a powerful continuous-time framework for sequence modeling, yet the roughness of the driving control path often restricts their efficiency. Standard splines introduce…
In medical imaging, accurate image segmentation is crucial for quantifying diseases, assessing prognosis, and evaluating treatment outcomes. However, existing methods lack an in-depth integration of global and local features, failing to pay…
Unsupervised Change Detection (UCD) in multimodal Remote Sensing (RS) images remains a difficult challenge due to the inherent spatio-temporal complexity within data, and the heterogeneity arising from different imaging sensors. Inspired by…
Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely…
This paper presents a novel approach for structure-preserving planar simplification of indoor scene point clouds for both simulated and real-world environments. Initially, the scene point cloud undergoes preprocessing steps, including noise…
Nowadays, skeleton information in videos plays an important role in human-centric video analysis but effective coding such massive skeleton information has never been addressed in previous work. In this paper, we make the first attempt to…
Cloud-edge collaboration enhances machine perception by combining the strengths of edge and cloud computing. Edge devices capture raw data (e.g., 3D point clouds) and extract salient features, which are sent to the cloud for deeper analysis…
Recognition of occluded objects in unseen indoor environments is a challenging problem for mobile robots. This work proposes a new slicing-based topological descriptor that captures the 3D shape of object point clouds to address this…
Most multi-view clustering methods are limited by shallow models without sound nonlinear information perception capability, or fail to effectively exploit complementary information hidden in different views. To tackle these issues, we…
Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This…
Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the field through existing methods, the sample-independent modeling…
Reconstructing 3D shapes from a single image plays an important role in computer vision. Many methods have been proposed and achieve impressive performance. However, existing methods mainly focus on extracting semantic information from…
Human action video recognition has recently attracted more attention in applications such as video security and sports posture correction. Popular solutions, including graph convolutional networks (GCNs) that model the human skeleton as a…
Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant…