Amir Arsalan Soltani

I am an AI researcher with prior research experience in research on building computational models of perceptions in 3D inspired by cognitive science to endow future AI agents with visual intelligence. I am lucky to be an affiliate of CoCoSci and CNCL.

I was fortunate to be a research assistant at Josh Tenenbaum's Computational Cognitive Science Lab at Massachusetts Institute of Technology.

I graduated in 2016 with a Master's Degree in Computer Science from State University of New York at Buffalo. Prior to that, I did my undergraduate at Isalamic Azad University in Iran, where I received my B.S. in Computer Software Engineering.

Email  /  Google Scholar  /  GitHub  /  LinkedIn  /  Twitter

Research

My long-term research goal is to enable AI agents to have the ability to imagine (produce mental or abstract imagery without sensory inputs) by building models of the visual world and come up with concise and generalizable theories/solutions that can explain phenomena beyond what low-level statistics of observable data spells.

Talks
Publications

Perception of 3D Shape Integrates Intuitive Physics and Analysis-by-Synthesis
Yildirim, I.*, Siegel, M.*, Soltani, A.*, Chaudhuri, S. & Tenenbaum, J.
(* indicate equal contribution)
Nature Human Behavior, 8(2) 320–335, 2023

Journal Article  /  Cover Article  /  PDF  /  Supplementary Materials  /  Tweet

Face recognition via inference in a causal generative model

Inverse Rendering Best Explains Face Perception Under Extreme Illuminations
Egger B., Siegel M., Arora R., Soltani AA., Yildirim I. & Tenenbaum J.
Cognitive Science Society (CogSci) , 2020
Abstract (PDF)  /  Poster (PDF)  /  Video  /  Tweet

Inspired by the idea of vision as inverse graphics, we propose a Bayesian model for face recognition that achieves both human-level and somewhat human-like performance on stimuli that humans do not have expure to normally

The Little Prince, uncovers the truth

Draping an Elephant: Uncovering Children's Reasoning About Cloth-Covered Objects
Ullman T., Kosoy E., Yildirim I., Soltani AA., Siegel M., Tenenbaum J. & Spelke E.
Cognitive Science Society (CogSci) , 2019
Paper (PDF)   

This work is a contribution towards The Core Object System. Here, we show that preschool children are able to use their "intuitive" physical knowledge of how cloths work and reason about what shape has been draped by cloth, hence uncovering the true object.

3D generation, 3D reconstruction
Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes with Deep Generative Networks
Soltani, AA., Huang, H., Wu, J., Kulkarni, T., & Tenenbaum, J.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017
Paper (PDF)  /  Code  /  Poster  /  Slides (includes more results)

A generative model for generic 3D shapes to obtain abstract description of objects as a crucial component for building models of the environment through inverse graphics.


website template credits