Neural fields in visual computing and beyond

Y Xie, T Takikawa, S Saito, O Litany… - Computer Graphics …, 2022 - Wiley Online Library
Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

MR-Net: Multiresolution sinusoidal neural networks

H Paz, D Perazzo, T Novello, G Schardong… - Computers & …, 2023 - Elsevier
We present MR-Net, a general architecture for multiresolution sinusoidal neural networks,
and a framework for imaging applications based on this architecture. We extend sinusoidal …

DSR: dynamical surface representation as implicit neural networks for protein

D Sun, H Huang, Y Li, X Gong… - Advances in Neural …, 2023 - proceedings.neurips.cc
We propose a novel neural network-based approach to modeling protein dynamics using an
implicit representation of a protein's surface in 3D and time. Our method utilizes the zero …

Neural Radiance Fields with Torch Units

B Ni, H Wang, D Bai, M Weng, D Qi, W Qiu… - arXiv preprint arXiv …, 2024 - arxiv.org
Neural Radiance Fields (NeRF) give rise to learning-based 3D reconstruction methods
widely used in industrial applications. Although prevalent methods achieve considerable …

Unsupervised deep network for image texture transformation: Improving the quality of cross-correlation analysis and mechanical vortex visualisation during cardiac …

D Mangileva, A Kursanov, L Katsnelson, O Solovyova - Heliyon, 2023 - cell.com
Visualisation of cardiac fibrillation plays a very considerable role in cardiophysiological
study and clinical applications. One of the ways to obtain the image of these phenomena is …

SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction

Y Lee, Z Zhang, D Fan - arXiv preprint arXiv:2405.17793, 2024 - arxiv.org
3D Gaussian Splatting (3DGS) has made a significant stride in novel view synthesis,
demonstrating top-notch rendering quality while achieving real-time rendering speed …

A Novel Hardware Accelerator of NeRF Based on Xilinx UltraScale and UltraScale+ FPGA

B Zhao, W Huang, Y Huang - 2023 33rd International …, 2023 - ieeexplore.ieee.org
Neural Radiance Fields (NeRF) has shown its superiority in various fields, including 3D
reconstruction and inverse rendering. However, due to its high computational demands …

Novel Image Super-resolution and Denoising Using Implicit Tensor-product B-spline

J Horváth, GM Su - Electronic Imaging, 2024 - library.imaging.org
In the dynamic realm of image processing, coordinate-based neural networks have made
significant strides, especially in tasks such as 3D reconstruction, pose estimation, and …

[引用][C] Split Activation Networks for Neural Fields

M Kilianovskyi - 2023