Related papers: Cortex-Synth: Differentiable Topology-Aware 3D Ske…

Point clouds are a set of data points in space to represent the 3D geometry of objects. A fundamental step in the processing is to identify a subset of points to represent the shape. While traditional sampling methods often ignore to…

While conventional computer vision emphasizes pixel-level and feature-based objectives, medical image analysis of intricate biological structures necessitates explicit representation of their complex topological properties. Despite their…

We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid…

This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional network (GCN) to model the human body manifold structure,…

Convolutional Neural Networks (CNN) have been widely deployed in diverse application domains. There has been significant progress in accelerating both their training and inference using high-performance GPUs, FPGAs, and custom ASICs for…

In real-world clinical practice, electrocardiograms (ECGs) are often captured and shared as photographs. However, publicly available ECG data, and thus most related research, relies on digital signals. This has led to a disconnect in which…

Medical image segmentation grapples with challenges including multi-scale lesion variability, ill-defined tissue boundaries, and computationally intensive processing demands. This paper proposes the DyGLNet, which achieves efficient and…

We describe a new approach to fit the polyhedron describing a 3D building model to the point cloud of a Digital Elevation Model (DEM). We introduce a new kinetic framework that hides to its user the combinatorial complexity of determining…

In recent years, action recognition has received much attention and wide application due to its important role in video understanding. Most of the researches on action recognition methods focused on improving the performance via various…

Graph Convolutional Networks (GCNs) have attracted increasing interests for the task of skeleton-based action recognition. The key lies in the design of the graph structure, which encodes skeleton topology information. In this paper, we…

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down…

Optimizing deep learning models is generally performed in two steps: (i) high-level graph optimizations such as kernel fusion and (ii) low level kernel optimizations such as those found in vendor libraries. This approach often leaves…

Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic segmentation is one the essential components of environmental…

Automatic segmentation of diverse heterogeneous brain lesions using multi-modal MRI is a challenging problem in clinical neuroimaging, mainly because of the lack of generalizability and high prediction variance of pathology-specific deep…

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…

Accurate segmentation of tubular structures in medical images, such as vessels and airway trees, is crucial for computer-aided diagnosis, radiotherapy, and surgical planning. However, significant challenges exist in algorithm design when…

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,…

Single image view synthesis allows for the generation of new views of a scene given a single input image. This is challenging, as it requires comprehensively understanding the 3D scene from a single image. As a result, current methods…

3D skeleton-based action recognition and motion prediction are two essential problems of human activity understanding. In many previous works: 1) they studied two tasks separately, neglecting internal correlations; 2) they did not capture…

Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its own sequence of events while simultaneously engaging in…