Hi! I'm Ainaz Eftekhar.

I am a last-year bachelor student in computer engineering at Sharif University of Technology. I'm also a visiting student at EPFL working at Visual Intelligence and Learning Laboratory (VILAB), under the guidance of Amir Zamir. I'm planning to start my graduate studies from Fall 2022.

My research interests are broadly in computer vision and machine learning. I'm interested in 3D vision as we all live in a 3D world. So if we want agents that can actively perceive and interact with their environment, we should be able to build systems that can understand the 3D structure of the world from the 2-dimensional images captured by cameras.

I’m also interested in the intersection of computer vision and cognitive science and methods inspired by vision development in biological systems (especially children). I'm excited about building artificial models that can develop visual perception through sensing the world in different modalities, exploring and interacting with their physical environment, and learning like a child.



Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans

Ainaz Eftekhar*, Alexander Sax*, Roman Bachmann, Jitendra Malik, Amir Zamir


Puzzle-AE: Novelty Detection in Images Through Solving Puzzles

Mohammadreza Salehi, Ainaz Eftekhar*, Niousha Sadjadi*, Mohammad Hossein Rohban, Hamid R. Rabiee



Visiting Student at EPFL

Visual Intelligence and Learning Lab (VILAB), EPFL

October 2021 – April 2022     .     Lausanne, Switzerland

Summer@EPFL Fellow

Visual Intelligence and Learning Lab (VILAB), EPFL

September 2020 – September 2021     .    Lausanne, Switzerland
Worked on a pipeline to create 'steerable' multi-task vision datasets by parametrically sampling and rendering 3D scans

Research Assistant

Robust and Interpretable Machine Learning Lab (RIML), Sharif University of Technology

September 2019 – September 2020     .     Tehran, Iran
Anomaly detection in images and videos

Summer Intern

Indian Institute of Technology

June 2019 – September 2019     .     Kharagpur, India
Reducing the effect of severe dataset imbalance by producing additional training examples using GANs