Lucas D. Young

ORCID: 0000-0003-1224-3977
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Image Processing Techniques
  • Image and Signal Denoising Methods
  • Image Processing Techniques and Applications
  • Advanced Vision and Imaging
  • Image Enhancement Techniques
  • Advanced Statistical Methods and Models
  • Reservoir Engineering and Simulation Methods
  • Neural Networks and Applications
  • Generative Adversarial Networks and Image Synthesis
  • Fault Detection and Control Systems
  • Oil and Gas Production Techniques
  • Drilling and Well Engineering

META Health
2022-2023

Meta (Israel)
2022

We propose an efficient neural network for RAW image denoising. Although network-based denoising has been extensively studied restoration, little attention given to compute limited and power sensitive devices, such as smartphones wearables. In this paper, we present a novel architecture suite of training techniques high quality in mobile devices. Our work is distinguished by three main contributions. (1) The Feature-Align layer that modulates the activations encoder-decoder with input noisy...

10.1109/wacvw54805.2022.00078 article EN 2022-01-01

A promising direction for recovering the lost information in low-resolution headshot images is utilizing a set of high-resolution exemplars from same identity. Complementary reference can improve generated quality across many different views and poses. However, it challenging to make best use multiple exemplars: alignment each exemplar cannot be guaranteed. Using low-quality mismatched as references will impair output results. To overcome these issues, we propose Headshot Image...

10.1109/wacv56688.2023.00174 article EN 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023-01-01

Abstract Synopsis The aim of this work is to present a PCP (Progressing Cavity Pumps) drive-head, which main feature its dynamic viscous brake and safe operation due the lack pulleys, belts external mobile parts. drive-head was result 3 years research investigation in joint effort between ITBA (University applied sciences) service company. final prototype after development installed at an operator’s well April 2012, where it performed optimal. results tests made during trial are shown...

10.2118/165026-ms article EN All Days 2013-05-21

Many tests for the analysis of continuous data have underlying assumption that in question follows a normal distribution (ex.ANOVA, regression, etc.).Within certain research topics, it is common to end up with dataset has disproportionately high number zero-values but otherwise relatively normal.These datasets are often referred as 'zeroinflated' and their can be challenging.An example where these zero-inflated arise plant science.We conducted simulation study compare performance...

10.14445/22315373/ijmtt-v65i8p516 article EN International Journal of Mathematics Trends and Technology 2019-08-25

A promising direction for recovering the lost information in low-resolution headshot images is utilizing a set of high-resolution exemplars from same identity. Complementary reference can improve generated quality across many different views and poses. However, it challenging to make best use multiple exemplars: alignment each exemplar cannot be guaranteed. Using low-quality mismatched as references will impair output results. To overcome these issues, we propose an efficient Headshot Image...

10.48550/arxiv.2203.14863 preprint EN cc-by arXiv (Cornell University) 2022-01-01

Downsampling is one of the most basic image processing operations. Improper spatio-temporal downsampling applied on videos can cause aliasing issues such as moir\'e patterns in space and wagon-wheel effect time. Consequently, inverse task upscaling a low-resolution, low frame-rate video time becomes challenging ill-posed problem due to information loss artifacts. In this paper, we aim solve space-time by learning downsampler. Towards goal, propose neural network framework that jointly learns...

10.48550/arxiv.2203.08140 preprint EN cc-by arXiv (Cornell University) 2022-01-01

We propose an efficient neural network for RAW image denoising. Although network-based denoising has been extensively studied restoration, little attention given to compute limited and power sensitive devices, such as smartphones smartwatches. In this paper, we present a novel architecture suite of training techniques high quality in mobile devices. Our work is distinguished by three main contributions. (1) Feature-Align layer that modulates the activations encoder-decoder with input noisy...

10.48550/arxiv.2103.01524 preprint EN other-oa arXiv (Cornell University) 2021-01-01
Coming Soon ...