Related papers: A Distributed GPU-based Framework for real-time 3D…
We introduce PointGauss, a novel point cloud-guided framework for real-time multi-object segmentation in Gaussian Splatting representations. Unlike existing methods that suffer from prolonged initialization and limited multi-view…
Background: Visualization of multi-channel microscopy data plays a vital role in biological research. With the ever-increasing resolution of modern microscopes the data set size of the scanned specimen grows steadily. On commodity hardware…
Training large-scale models relies on a vast number of computing resources. For example, training the GPT-4 model (1.8 trillion parameters) requires 25000 A100 GPUs . It is a challenge to build a large-scale cluster with one type of…
Finite element schemes based on discontinuous Galerkin methods possess features amenable to massively parallel computing accelerated with general purpose graphics processing units (GPUs). However, the computational performance of such…
The development of composable systems architecture marks a significant shift in resource allocation and utilization within data centers. This paper presents a composable architecture scaling up to 32 GPUs on a single node, addressing the…
We present distributed algorithms for training dynamic Graph Neural Networks (GNN) on large scale graphs spanning multi-node, multi-GPU systems. To the best of our knowledge, this is the first scaling study on dynamic GNN. We devise…
We present a voxel-based rendering pipeline for large 3D line sets that employs GPU ray-casting to achieve scalable rendering including transparency and global illumination effects that cannot be achieved with GPU rasterization. Even for…
3DGS is an emerging and increasingly popular technology in the field of novel view synthesis. Its highly realistic rendering quality and real-time rendering capabilities make it promising for various applications. However, when applied to…
Spatial join is a fundamental operation in spatial databases. With the rapid growth of 3D data in applications such as LiDAR-based object detection and 3D digital pathology, there is an increasing need to support spatial join over 3D…
The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large-scale 3DGS and rendering it in real-time across various…
Virtual Reality systems provide many opportunities for scientific research and consumer enjoyment; however, they are more demanding than traditional desktop applications and require a wired connection to desktops in order to enjoy maximum…
Astronomical researchers often think of analysis and visualization as separate tasks. In the case of high-dimensional data sets, though, interactive exploratory data visualization can give far more insight than an approach where data…
3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, a key requirement for immersive applications. However, the extension of 3DGS to dynamic scenes remains limitations on the substantial data volume of dense Gaussians and…
The ALICE Collaboration at CERN developed a 3D visualisation tool capable of displaying a representation of collected collision data (particle trajectories, clusters and calorimeter towers) called the Event Display. The Event Display is…
3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and…
This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…
We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas. Existing works are not well suited for applications like mixed-reality or closed-loop simulation due to their limited…
The spatially-varying field of the human visual system has recently received a resurgence of interest with the development of virtual reality (VR) and neural networks. The computational demands of high resolution rendering desired for VR…
DBSCAN is a well-known density-based clustering algorithm to discover arbitrary shape clusters. While conceptually simple in serial, the algorithm is challenging to efficiently parallelize on manycore GPU architectures. Common pitfalls,…
Existing learning-based methods for point cloud rendering adopt various 3D representations and feature querying mechanisms to alleviate the sparsity problem of point clouds. However, artifacts still appear in rendered images, due to the…