I study how machines perceive and understand the world: depth, geometry, interaction, and vision–language grounding. I work at the intersection of classical vision (homography, stitching, geometry) and deep models for perception and control.
Research: 3D reconstruction, depth estimation, multi-camera stitching,
robustness in autonomous driving perception.
Also exploring: Persian text-to-speech models that can imitate professional announcers with minimal audible artifacts.
Research interests
3D computer vision & reconstruction
Robotic language–vision models
3D interaction
Augmented reality
Education
Sharif University of Technology,
(2020 - 2025)
Atomic Energy Highschool,
(2017 - 2020)
Research / Projects
Research experience
3D Depth Map for the Application of Autonomous Vehicles —
Built panoramic stitched views from multi-camera images using homography + EWMA to cover blind spots.
Analyzed nuScenes with DeepInteraction for object detection and depth robustness.
Project repo
Persian Text-to-Speech —
Designed a TTS system to mimic professional announcers with minimal perceptual difference from real speech, targeting continuous broadcast use.
Technical work
Numerical Computations — Coding Guides —
Authored Jupyter notebooks and Python implementations to support Numerical Computations students.
Course-Materials repo
Course GPT —
A full-stack course planner / generator app (React + Django).
Worked on UI (React/MUI) and coordination with Django backend API.
Frontend repo
Industry experience
Front-End Developer — Avan Holding (Adowing),
LinkedIn
(Mar 2024 – Mar 2025)
Built internal tools for employees (profiles, interests, task tracking, timers) using Next.js, TypeScript, Tailwind CSS, DaisyUI, Redux.
Focused on shipping usable interfaces in production.
Front-End Developer — Kafshbaf,
Website
(Mar 2025 – Aug 2025)
Worked on a bilingual B2B marketplace (suppliers ↔ bulk buyers).
Stack: Next.js, TypeScript, Tailwind CSS, Shadcn.
Collaborated with backend and DevOps to align UI with business needs.
Teaching Assistant
Web Programming,
Dr. Abrishami
(Fall 2025) —
Product Owner of the course project: defined features with student teams, assigned sprint tasks, ran weekly check-ins.
Web Programming,
Dr. Poursoltani
(Spring 2025) —
Product Owner of the course project: defined features with student teams, assigned sprint tasks, ran weekly check-ins.
Software Engineering,
Dr. Rivadeh (Spring & Fall 2025) —
Helped design quizzes and final exam questions; graded exam responses.
Scientific & Technical Presentation,
Prof. Kasaei
(Fall 2024, Spring & Fall 2025) —
Guided infographic design, reviewed presentations, and graded assignments.
Signals & Systems,
Prof. Sameti (Fall 2024) —
Designed and graded a hands-on coding assignment.
Basic Programming,
Dr. Arminpour (Spring 2024) —
Wrote assignments on functional programming and file management, designed the final project, supervised exams.
Probability & Statistics,
Dr. Najafi (Fall 2023) —
Authored and graded several quizzes.
Numerical Computations,
Hossein Esfandiari (Spring 2023 & Fall 2023) —
Built coding assignments and an implementation guide for students.