Shreshth Saini

Research Engineer (AI)

Arkray Inc.


I am a PhD student at the Laboratory for Image and Video Engineering (LIVE) at University of Texas at Austin. I am advised by Professor Alan C Bovik. My current research focus is on computer vision, deep learning, and high dynamic range video content.

Before this, I have worked as Research Engineer/Machine Learning Engineer at BioMind, Singapore and as Research Engineer - AI at Arkray, Inc.. Where I worked on developing industry leading medical AI solutions. Notably, I have been working on challenging pathological datasets to develope highly reliable and light deep learning models which could be deployed on devices like Aution-Eye.

My research interest is highly interdisciplinary covering machine learning, computer vision, video engineering,medical image analysis, and healthcare informatics. I am tinkering around MLOps more recently, I welcome any suggestion and/or guidance. I occasionally work on deep learning applications in biometrics (fact: I started my research journey from this field).

I completed my B.Tech in Electrical Engineering from Indian Institue of Technology, Jodhpur in 2020. I was fortunate to be advised by Dr. Mengling ‘Mornin’ Feng at Healthcare AI group, National University of Singapore(NUS). During my undergrad, I was actively working with Dr. Anil Kumar Tiwari, Dr. Rajendra Nagar, and Dr. Deepak Mishra in biomedical and healtcare analytics, and computer vision. I am eternally greatful to Dr. Aditya Nigam, who identified and steered my research interest early in my undergrad.


  • Machine Learning
  • Deep Learning
  • Computer Vision
  • Video Engineering
  • Video Quality Assessment
  • Medical Image Analysis & Healthcare Informatics
  • Biometrics


  • PhD (ECE), 2022-2026

  • B.Tech (EE), 2016-2020

    IIT Jodhpur

Recent Publications

Quickly discover relevant content by filtering publications.

(M)SLAe-Net: Multi-Scale Multi-Level Attention embedded Network for Retinal Vessel Segmentation

Segmentation plays a crucial role in diagnosis. Studying the retinal vasculatures from fundus images help identify early signs of many …

B-SegNet: branched-SegMentor network for skin lesion segmentation

Melanoma is the most common form of cancer in the world. Early diagnosis of the disease and an accurate estimation of its size and …

M2SLAe-Net: Multi-Scale Multi-Level Attention embedded Network for Retinal Vessel Segmentation(Abstract Presentation)

Segmentation plays a crucial role in diagnosis. Studying the retinal vasculatures from fundus images help identify early signs of many …



Graduate Research Assistant

Laboratory for Image and Video Engineering (LIVE), UT Austin

Aug 2022 – Present Austin, United States
Supervisor: Prof. Alan C Bovik

Research Engineer/Machine Learning Engineer

BioMind, Singapore

Feb 2022 – Jun 2022 Singapore, Singapore

Research Engineer(AI)

Arkray, Inc.

Aug 2020 – Dec 2021 Pune, India

Research Assistant

Saw Swee Hock School of Public Health, NUS-Singapore

May 2019 – Jul 2019 Singapore

Undergraduate Researcher

Image Processing and Computer Vision Lab, IIT Jodhpur

Aug 2018 – Aug 2020 Jodhpur, India

Research Intern

The Multimedia Analytics, Networks and Systems Lab, IIT Mandi

May 2018 – Jul 2020 Mandi, India
Supervisor: Dr. Aditya Nigam


Academic and Research

  • Oral presentation at IEEE-ICHI, 2021
  • Oral and Poster presentation at ACM-CHIL, 2021
  • Poster presentation at IEEE-ISBI, 2021
  • Multipath Super Resolution Network with Novel loss, EE Department, IIT Jodhpur, 2020
  • Oral and Poster presentation at NCVPRIPG, 2019
  • Skin Lesion Analysis, NUS-MIT Datathon, NUS-Singapore, 2019
  • Cardiac Image Segmentation(3D Data), IIT Jodhpur, 2019
  • Deep Learning for Medical Image Analysis, LAMBDA-Group, IIT Jopdhpur, 2019
  • Convolutional Neural Networks, Workshop on Applied Deep Learning, IIT Mandi, 2018

Co-Curricular and Extra-Curricular

  • Startup ecosystems in Tier-2 cities, Idea Saprk - Entrepreneurship Club, IIT Jodhpur, 2018
  • Entrepreneurial Initiatives, panel discussion, IIT Jodhpur, 2019
  • Atronomical Image Processing, Astronomy Club, IIT Jodhpur, 2017

Position of Responsibilities

Recent Posts

Variational AutoEncoder

In deep learning, Variational autoencoders (VAEs) is a technique for learning latent representations. They are also used in a number of …

Supprt Vector Machine (SVM)

A Support Vector Machine (SVM) is a discriminative classifier formally defined by a separating hyperplane. In other words, given …

Genome sequencing

Sequencing of genomes is an important land mark that humanity has achieved as it opens door to various explorations such as …