I'm AmirHossein Razlighi.

I'm an enthusiastic Computer Vision Researcher. I am continuously seeking new opportunities to learn in the field of Computer Vision and Machine Learning. I am also a big fan of Intersection of Computer Vision and Computer Graphics and also Robotics.

Scroll Down

About Me

I'm currently a last-year undergraduate student in Computer Engineering at Sharif University of Technology (the best university in Iran, according to QS ranking 2023). My research interests are among intersection of these areas: 1) Computer Vision, 2) 3D Computer Vision & Computer Graphics, and 3) Robotics. I think that combination of these areas, will make a new revolution in our lives, bringing us Fully Autonomous Vehicles, Assistant Robots and replacing smart phones woth smart glasses. All of these will happen if we can make the world perceptible for machines, going further than human perception! I am continuously seeking researches related to these subjects and have done some projects untill now, which brought me a lot of learning opportunities.


Education

Sharif University of Technology

BSc. Student in Computer Engineering October 2020 - Present

Cumulative GPA: 19.39/20.0 | Major GPA: 19.65/20.0 | Ranked in top 10% among 194 students

Salam High School

Diploma in Mathematics and Physics 2016-2019

GPA: 19.86/20.0

Industrial Experiences

Tapsi Co.

Junior AR Systems Engineer Feb 2022 - Sep 2022

( This job is related to my university CO-OP program )

  • First member of the R&D team called Tapsi Lab focused on using computer vision to change user experience in ride-hailing industry.
  • Developed the Driver-Arrived AR project from-scratch, which was capable of detecting the position of driver using integration of camera and GPS data.
  • Use web-based technologies like Tensorflow.js to run the whole AR experience client-side.
  • Made a customized version of ”AR.js” library and developed on top of it for custom rendering and integration of data.
  • Communicated with many different teams to build up this entire project, including design, management team, business team, and DevOps team.

Research Experiences

University of Toronto

Research Assistant (Summer Internship) Jun 2023 - May 2023

  • Supervisors: Dr. Florian Shkurit and Dr. Animesh Garg
  • Worked on the subject of vision-based robotic manipulation.
  • Studied generalized 3d scene encoding and reconstruction using NeRF models.
  • Implemented and customized SRT (scene representation transformer) in our pipeline.
  • Customized the ARNOLD dataset for retrieving canonical cube views of the robot scene. (LINK)
  • Worked on the Google’s PerAct model and its dataset and implemented custom agents to run and evaluate in IsaacSim simulator.
  • The pre-print version of the paper and some of the outcomes can be found here

ETH University

Research Assistant Jun 2023 - July 2024

  • Supervisor: Dr. Danda Pani Paudel
  • Worked on the subject of NeRF models for 3D reconstructing the dynamic scenes.
  • Studied the usage of SDFs and how to disentangle geometry and appearance in NeRF models.
  • Worked on how to do morphing between 2 SDFs based on RGB images only.
  • Designed regularizers based on SDF properties for continuous learning of morphing in inverse-rendering.
  • You can see the related recommendation letters about this experience on my LinkedIn

INSAIT

Summer Research Intern Jun 2024 - Oct 2024

  • Supervisor: Dr. Danda Pani Paudel
  • This project was a continued effort on the project that was started during my work at ETH with Dr. Paudel.
  • Worked on the subject of Dynamic 3D Reconstruction using Signed-distance functions (SDFs) and how to integrate it into the Gaussian Splatting pipeline.
  • Created a dataset of challenging deformable scenes (like a breaking sphere, a growing plant, and etc.)
  • Designed and implemented a complete pipeline of Encoding the 3D scene, reconstructing the geometry and the color.
  • You can see the related recommendation letters about this experience on my LinkedIn

Skills

I am continuously learning and seeking new opportunities to gain experience and cooperate with experts. I had the honor of working with great people and learning from them until now and I gained many skills which I hope I can improve them more in the future.

  • Computer Vision
  • Machine Learning
  • PyTorch
  • Tensorflow
  • Augmented Reality Frameworks
  • Research and Development (R&D)

Volunteering Activities

Teacher Assistant

Sharif University of Technology Oct 2021 - Present

Important Note:

None of the TA positions in my university are paid and/or contract-based. All of my TA experiences are voluntarily.

I continuously seek opportunities to share my knowledge and learn more from interacting with people who are active in the field. One of the best societies to be active and learn from, is undergrad students. I became TA in different roles and different courses to make my knowledge from these courses more complete and learn more and more by designing homeworks and answering questions of students. Some of the most important activities of mine in this area are:
  • Teaching Assistant of Adv. 3D Computer Vision (Graduate-level course): I am responsible for designing quizes on the subject of ”Multi-view reconstruction” and ensuring the quality of homework questions on this subject. I am also responsible for teaching a series of lectures on the subject of NeRF and Gaussian Splatting.
    Lecturer: Prof. Shohreh Kasaei
  • Teaching Assistant of Modern Information Retrieval (Head of Project): Head of designing projects and managing a team of people focusing on designing course's final project, in 3 phases: Classical IR Methods and Web IR, ML in IR, Deep methods for information retrieval and using LLMs.
    Lecturer: Dr. Mahdieh Soleymani
  • Head Teaching Assistant of Machine Learning (Project section): managing a team of 10 people focusing on designing course's final project, focusing on Computer Vision and Natural Language Processing topics. I was also responsible for holding some TA Classes about theoretical and practical topics on ML.
    Lecturer: Dr. Fatemeh Seyed Salehi
  • Teaching Assistant of Convex Optimization: responsible for designing questions for Convex functions subject and I was also manager of a team of TAs responsible for designing and grading the homework on Duality subject.
    Lecturer: Dr. Amir Najafi
  • Teaching Assistant of Digital Image Processing (Graduate-level course): Designing slides of deep learning in computer vision | Teaching deep-learning sessions | Designing a homework and a quiz on "Image Transformations" | designing a quiz on "Morphological operations"
    Lecturer: Prof. Shohreh Kasaei
  • Head Teaching Assistant of Scientific and Technical Presentation Lecturer: Prof. Shohreh Kasaei
  • Teaching Assistant of Artificial Intelligence: Designer of Computer Vision project | Lecturer: Dr. Mohammad Hossein Rohban
  • Teaching Assistant of Artificial Intelligence: Head Of Designing the course's final project. | Lecturers: Dr. Mohammad Hossein Rohban, Dr. Mahdieh Soleymani
  • Teaching Assistant of Fundamentals of Computer Vision: Head of workshops & responsible for designing excersices on 3D Vision | Lecturer: Prof. Shohreh Kasaei
  • Teaching Assistant of Database Desgin | Lecturer: Dr. M. Varmazyar
  • Teaching Assistant of Linear Algebra (2 semesters): Head of re-designing the whole slides of the course & Responsible for designing a theoretical excersice | Lecturer: Dr. Maryam Ramezani
  • Teaching Assistant of Probability and Statistics | Lecturer: Dr. Mahdi Jafari
  • Teaching Assistant of Advanced Programming in Java (for 3 semesters): Responsible for holding 3 workshops on OOP & Designing the GUI phase of the project

Voluntarily Activities in other areas

Sharif University of Technology | University of Toronto Oct 2021 - Present

I also have many voluntarily activities in the different societies and seminars in the Computer Engineering Department. Some of the most important ones are:

  • Vice President of Students' Scientific Chapter(SSC)
  • Head of Technical Beta Team (at 8th WSS): I started the idea to make an R&D team in WSS. This team (called "Technical Beta") is responsible to design a new chatbot that tries to have conversation with users. In first version, we are trying to train our model on "FAQ" data(from previous years) to help people get their answers A.S.A.P! look at this repo for more information on our work
  • Founder of Byte Publication: Link to the Publication
  • Enrolled for "RTI" Program (Oxford University)
  • A member of "3D Vision" reading group(University of Toronto)

Outcomes of my research projects:

N4DE: Neural 4D Evolution under Large Topological Changes from 2D Images

AmirHossein Naghi Razlighi, Tiago Novello, Asen Nachkov, Thomas Probst, Danda Paudel
breaking Sphere
deforming chair

This paper is the outcome of my collaboration with Dr. Paudel at ETH and then as an intern at INSAIT. The paper is submitted to CVPR 2025 and is under review.

View it on arXiv

MARS: Multi-task Action Prediction for Robot Manipulation based on Scene Representation

Haoping Xu, Richard Hanxu*, AmirHossein Naghi Razlighi*, Alàn Aspuru-Guzik, Florian Shkurti, Animesh Garg
Model Architecture

This paper is the outcome of my summer internship at University of Toronto. The paper introduces a new methods for predicting multi-task actions for robot manipulation based on scene representation. This is a pre-print version of the paper.

View PDF

Some of my projects which I have done untill now (Github)