Related papers: DCCVT: Differentiable Clipped Centroidal Voronoi T…
Deep learning and the collocation method are merged and used to solve partial differential equations describing structures' deformation. We have considered different types of materials: linear elasticity, hyperelasticity (neo-Hookean) with…
In this paper, the Discontinuous Cell Method (DCM) is formulated with the objective of simulating cohesive fracture propagation and fragmentation in homogeneous solids without issues relevant to excessive mesh deformation typical of…
Music source separation (MSS) aims to extract 'vocals', 'drums', 'bass' and 'other' tracks from a piece of mixed music. While deep learning methods have shown impressive results, there is a trend toward larger models. In our paper, we…
Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes. This non-uniformity, however, leads to irregularity in the mesh structure,…
Reconstructing 3D point clouds into triangle meshes is a key problem in computational geometry and surface reconstruction. Point cloud triangulation solves this problem by providing edge information to the input points. Since no vertex…
In the field of 3D medical imaging, accurately extracting and representing the blood vessels with curvilinear structures holds paramount importance for clinical diagnosis. Previous methods have commonly relied on discrete representation…
We present Deformable Voxel Grids (DVGs) for 3D shapes comparison and processing. It consists of a voxel grid which is deformed to approximate the silhouette of a shape, via energy-minimization. By interpreting the DVG as a local…
Point cloud segmentation (PCS) aims to make per-point predictions and enables robots and autonomous driving cars to understand the environment. The range image is a dense representation of a large-scale outdoor point cloud, and segmentation…
We introduce a supervised-learning framework for non-rigid point set alignment of a new kind - Displacements on Voxels Networks (DispVoxNets) - which abstracts away from the point set representation and regresses 3D displacement fields on…
Medical image segmentation leverages topological connectivity theory to enhance edge precision and regional consistency. However, existing deep networks integrating connectivity often forcibly inject it as an additional feature module,…
We present DeepVesselNet, an architecture tailored to the challenges faced when extracting vessel networks or trees and corresponding features in 3-D angiographic volumes using deep learning. We discuss the problems of low execution speed…
With the rapid advancements in digital imaging systems and networking, low-cost hand-held image capture devices equipped with network connectivity are becoming ubiquitous. This ease of digital image capture and sharing is also accompanied…
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…
This article provides next step towards solving speed bottleneck of any system that intensively uses convolutions operations (e.g. CNN). Method described in the article is applied on deformable part models (DPM) algorithm. Method described…
Purpose: To implement a brain segmentation pipeline based on convolutional neural networks, which rapidly segments 3D volumes into 27 anatomical structures. To provide an extensive, comparative study of segmentation performance on various…
Recent video codecs with multiple separable transforms can achieve significant coding gains using asymmetric trigonometric transforms (DCTs and DSTs), because they can exploit diverse statistics of residual block signals. However, they add…
This work introduces a new unsupervised representation learning technique called Deep Convolutional Transform Learning (DCTL). By stacking convolutional transforms, our approach is able to learn a set of independent kernels at different…
Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…
We present Deformable PV-RCNN, a high-performing point-cloud based 3D object detector. Currently, the proposal refinement methods used by the state-of-the-art two-stage detectors cannot adequately accommodate differing object scales,…
The non-uniformly distributed nature of the 3D dynamic point cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud…