Alireza Moazeni

hello.

I AM Alireza

& I am a Ph.D. student in computing science. Download My CV

about me

My research interests are in Computer Vision, Machine Learning, Generative Models, and Reinforcement Learning.

Personal Details

Full Name	:	First Name: Alireza Last Name: Moazeni
Address	:	Burnaby, BC V5A 1S6, Canada
Email	:	alisampo1375@gmail.com
Skype ID	:	amoazeni75
Google Scholar	:	Click Here!
Social Media	:

education

Ph.D. Student Sep. 2021 - Present

Ph.D. student in Computer Science at Simon Fraser University, Vancouver, Canada.
Bachelor of Science 2015 - 2020

I studied Computer Engineering focused on Artificial Intelligence and Computer Networks at Amirkabir University of Technology, Tehran, Iran.
I also have my minor in Electrical Engineering (Control Branch) department.
High School 2011 - 2015

I received my diploma in Mathematics and Physics discipline from the National Organization for Development of Exceptional Talents (NODET), Tehran, Iran.

Publications

publications

PAPR: Proximity Attention Point Rendering - Neural Information Processing Systems (NeurIPS), 2023 (Spotlight)

Authors: Yanshu Zhang*, Shichong Peng*, Alireza Moazeni, Ke Li

Abstract
Learning accurate and parsimonious point cloud representations of scene surfaces from scratch remains a challenge in 3D representation learning. Existing point-based methods often suffer from the vanishing gradient problem or require a large number of points to accurately model scene geometry and texture. To address these limitations, we propose Proximity Attention Point Rendering (PAPR), a novel method that consists of a point-based scene representation and a differentiable renderer. Our scene representation uses a point cloud where each point is characterized by its spatial position, foreground score, and view-independent feature vector. The renderer selects the relevant points for each ray and produces accurate colours using their associated features. PAPR effectively learns point cloud positions to represent the correct scene geometry, even when the initialization drastically differs from the target geometry. Notably, our method captures fine texture details while using only a parsimonious set of points. We also demonstrate four practical applications of our method: geometry editing, object manipulation, texture transfer, and exposure control.
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis - Neural Information Processing Systems (NeurIPS), 2022 (Spotlight)

Authors: Shichong Peng, Alireza Moazeni, Ke Li

Abstract
A persistent challenge in conditional image synthesis has been to generate diverse output images from the same input image despite only one output image being observed per input image. GAN-based methods are prone to mode collapse, which leads to low diversity. To get around this, we leverage Implicit Maximum Likelihood Estimation (IMLE) which can overcome mode collapse fundamentally. IMLE uses the same generator as GANs but trains it with a different, non-adversarial objective which ensures each observed image has a generated sample nearby. Unfortunately, to generate high-fidelity images, prior IMLE-based methods require a large number of samples, which is expensive. In this paper, we propose a new method to get around this limitation, which we dub Conditional Hierarchical IMLE (CHIMLE), which can generate high-fidelity images without requiring many samples. We show CHIMLE significantly outperforms the prior best IMLE, GAN and diffusion-based methods in terms of image fidelity and mode coverage across four tasks, namely night-to-day, 16× single image super-resolution, image colourization and image decompression. Quantitatively, our method improves Fréchet Inception Distance (FID) by 36.9% on average compared to the prior best IMLE-based method, and by 27.5% on average compared to the best non-IMLE-based general- purpose methods.

Honors

honors

Helmut & Hugo Eppich Family Scholarship - Ebco Eppich Award Competition

Simon Fraser University, British Columbia, Canada. 2022-2023

Offered for Helmut & Hugo Eppich Family Grad Schol - 2022-23 Ebco Eppich Award Competition.
Established in 2013, the Helmut and Hugo Eppich Family Scholarship provides financial support to a graduate student whose research is relevant to the area of Intelligent Systems.
Direct Admission to graduate school (Ph.D.) in Computer Science

Simon Fraser University, Vancouver, Canada. Dec. 2020

Offered for Direct Admission to graduate school (Ph.D.) in Computer Science - Artificial Intelligence.
Direct Admission to graduate school (Master of Science) in Computer Engineering

Amirkabir University of Technology, Tehran, Iran. Sep. 2020

Offered for Direct Admission to graduate school (Master of Science) in Computer Engineering - Artificial Intelligence, without taking the Nationwide University Entrance Exam for M.Sc. as a reward of academic records and achievements.
B.Sc. in Computer Engineering

Amirkabir University of Technology, Tehran, Iran. Sep. 2020

Ranked in the top 5% among about 100 undergraduate students in Computer Engineering and IT Department.
Minor Student in Electrical Engineering

Amirkabir University of Technology, Tehran, Iran. Sep. 2017

Ranked 4th among about 35 undergraduate students in Electrical Engineering (Control Engineering Department)(over 92 credits).
University Entrance Exam for B.Sc. in Math. and Engineering

Tehran, Iran. Sep. 2015

Achieved top 0.15 % place among all applicants of the Nationwide University Entrance Exam for B.Sc. in Math and Engineering (Approximately 250000 applicants).
RoboCup IRAN OPEN 2013

Tehran, Iran. April 2013

2nd place in League Junior Soccer B Light Weight in RoboCup IranOpen 2013 Competitions, April 5-7.
Helli (NODET) RoboCup 2013

Tehran, Iran. Jan. 2013

1st place in League Junior Soccer B Light Weight in RoboCup Helli (NODET) 2013 Competitions, January 13-15.
Mathematic and Aanalytic Geometry Competitions

Ministry of Science, Tehran, Iran. Nov. 2010

1st place in the National Conference on mathematics, analytic geometry and spatial orientation from Ministry of Science 2010.

My Skills

Professional Skills

Python

90%

C++ (Qt)

90%

Java

80%

Assembly

70%

PHP

70%

JavaScript

65%

HTML5

80%

CSS3

80%

Frameworks and Toolkits
                                PyTorch
Tensorflow 2
Keras
OpenCV
Django
Laravel (PHP)
Vue.js
jQuery
MySQL
PostgreSQL
Bootstrap
Wordpress
                                    
Anaconda

                                
                              
IDEs
                                IntelliJ IDEA
PyCharm
Visual Studio (C++, C#)
XCode (ios Development)
Qt Desktop
Spyder
Eclipse
PhpStorm
Atmel Studio
Code Vision
GNS3
Boson NetSim
Proteus
Altium Designer
Model Sim SE
Code Block(c++)

                                
                              
Others
                                Blockchain and Cryptocurrency
Git
VHDL
Verilog
Linux OS (Kali, Ubuntu, Debian, Lubuntu (embedded systems))
Adobe Photoshop
MVC Pattern
Command line Inteface
Miscrosoft Office Word
Miscrosoft Office Excel
Miscrosoft Office Powerpoint
Miscrosoft Office Access
Embedded boards (Raspberry Pi, NanoPC)
AVR

                                
                              

Work Experience

The only source of knowlege is experience.

Albert Einstein.

Teacher Assistant of Machine Learning Course

Spring 2022, Spring 2023

Reponsibilities: As a member of the Machine Learning Group, I was responsible for designing exercises, correcting exercises, and answering students' problems and questions.
Simon Fraser University, Vancouver, Canada.

Laboratory Instructor, C Programming

Sept. 2020 - Feb. 2021

Reponsibilities: Instruction and providing exercises for the basic programming course to 24 newly admitted bachelor students at Amirkabir University of Technology, Tehran, Iran.

Teacher Assistant of IoT

Sept. 2020 - Feb. 2021

Reponsibilities: As a member of the Internet of Things Teaching Assistants Group, I was responsible for designing exercises, correcting exercises, and answering students' problems and questions. Amirkabir University of Technology, Tehran, Iran.

Head of Teaching Assistants team of the algorithm design course

Sept. 2020 - Feb. 2021

As the head of the teaching assistant team, I was responsible for planning and designing lesson exercises, creating coordination between the teaching staff members, and designing online exams.
Amirkabir University of Technology, Tehran, Iran.

A.I. Developer and Product Manager

May 2016 - Aug. 2020

Responsibilities: In the i-Cliqq company, we developed Maya iBox (intelligent Box), an intelligent system containing an embedded board like Raspberry Pi or Nano PC with a smart program developed based on C++ (Qt) in Linux. Maya iBox is an innovation in the world of embroidery digitizing software using the latest programming technologies and involving artificial intelligence, image processing technics, and graph theory to make auto digitizing results usable and practical. Tehran, Iran <-> Zhuji, China

Teacher Assistant of Computational Intelligence

Sept. 2019 - Feb. 2020

Reponsibilities: As a member of the Computational Intelligence Teaching Assistants Group, I was responsible for designing exercises, correcting exercises, and answering students' problems and questions.
Amirkabir University of Technology, Tehran, Iran.

Teacher Assistant of Computer Networks

Sept. 2019 - Feb. 2020

Reponsibilities: As a member of the Computer Networks Teaching Assistants Group, I was responsible for designing exercises, correcting exercises, and answering students' problems and questions.
Amirkabir University of Technology, Tehran, Iran.

Teacher Assistant of Data structures and Algorithms Design

Feb. 2019 - July 2019

Reponsibilities: As a member of the Data structures and Algorithms Design Teaching Assistants Group, I was responsible for designing exercises, correcting exercises, and answering students' problems and questions.
Amirkabir University of Technology, Tehran, Iran.

S.Alireza Moazeni

Summary about me!