PU-Transformer: Point Cloud Upsampling Transformer

PU-Net: Point Cloud Upsampling Network

Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multilevel features per point and expand the point set via a multibranch convolution unit implicitly in feature space. The expanded feature is then split to a multitude of f...

Whegs Transformer

Transformer proteins

Proteins are generally believed to adopt a unique fold, defined by their amino acid sequence, under specific environmental conditions. These unique structures, in turn, endow proteins with one specific function. However, not all proteins obey the “1 amino acid sequence → 1 fold → 1 function” scheme. Moonlighting proteins that adopt one distinct threedimensional structure but can accomplish two ...

Image Transformer

Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a recently proposed model architecture based on self-attention, the Transformer, to a sequence modeling formulation of image generation with a tractable likelihood....

Transformer in Grid

The aim of this research article is to determine the way to install surge arresters close to a power transformer to provide protection against lightning overvoltage. Depending on the length of the cables used in the installation, the insulation levels in base insulators of surge arresters and bushings of transformers change according to the voltage they support. For validation purposes, the vol...