Vahe Taamazyan

Vahe Taamazyan

Senior Research Scientist · 3D Computer Vision for Robotics

About

Hey there! I'm a Senior Imaging Scientist at Intrinsic, where I help robots see. Fingers crossed that once they see the beauty of the world, they'll reconsider taking over!

I focus on research in 3D computer vision, work on fun side projects, and occasionally write down my ideas. Feel free to explore!

My Work

arXivBot
[011] Project 2026

arXivBot

Released: 2026

An LLM bot that reads every new cs.CV paper on arXiv so I don't have to, and emails me the relevant ones every morning. Hasn't missed a relevant paper yet, and runs entirely on free tiers.

Code About
3D-Object Perception Transformer (3PT) Thumbnail
[010] Paper 2026

3D-Object Perception Transformer (3PT)

Agastya Kalra, Tim Salzmann, Guy Stoppi, Dmitrii Marin, Rishav Agarwal, Vage Taamazyan, Martin Bokeloh, Stefan Hinterstoisser, Anton Boykov, Alberto Dall'Olio, Pravin Dangol, Kartik Venkataraman, Huaijin Chen • CVPR 2026 Highlight

PDF Project Page
5toguess
[009] Project 2025

5toguess

Released: 2025

A daily word-guessing game: one hidden word, five image clues, five guesses — reveal more clues at the cost of guesses. The games create themselves: an AI agent generates each puzzle and another AI plays it blind to validate the difficulty.

Link About
LookAtArts
[008] Project 2025

LookAtArts

Released: 2025

A daily visual meditation — one artwork a day from the Met's open-access collection, presented with nothing competing for your attention. No feed, no scrolling, just one piece of art and time to look at it.

Link About
A Plenoptic 3D Vision System Thumbnail
[007] Paper 2024

A Plenoptic 3D Vision System

Agastya Kalra, Vage Taamazyan, Alberto Dall'Olio, Raghav Khanna, Tomas Gerlich, Georgia Giannopoulou, Guy Stoppi, Daniel Baxter, Abhijit Ghosh, Rick Szeliski, Kartik Venkataraman • SIGGRAPH Asia 2024

PDF Project Page
Collision Avoidance Metric for 3D Camera Evaluation Thumbnail
[006] Paper 2024

Collision Avoidance Metric for 3D Camera Evaluation

Vage Taamazyan, Alberto Dall'olio, Agastya Kalra • CVPR VLADR 2024

PDF Code
Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation Thumbnail
[005] Paper 2024

Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation

Agastya Kalra, Guy Stoppi, Dmitrii Marin, Vage Taamazyan, Aarrushi Shandilya, Rishav Agarwal, Anton Boykov, Tze Hao Chong, Michael Stark • CVPR 2024

PDF Code
Deep polarization cues for transparent object segmentation Thumbnail
[004] Paper 2020

Deep polarization cues for transparent object segmentation

Agastya Kalra, Vage Taamazyan, Supreeth Krishna Rao, Kartik Venkataraman, Ramesh Raskar, Achuta Kadambi • CVPR 2020

PDF
Depth sensing using geometrically constrained polarization normals Thumbnail
[003] Paper 2017

Depth sensing using geometrically constrained polarization normals

Achuta Kadambi, Vage Taamazyan, Boxin Shi, Ramesh Raskar • IJCV 2017

PDF
Shape from Mixed Polarization Thumbnail
[002] Paper 2016

Shape from Mixed Polarization

Vage Taamazyan, Achuta Kadambi, Ramesh Raskar • arXiv preprint 2016

PDF
Polarized 3D: High-quality depth sensing with polarization cues Thumbnail
[001] Paper 2015

Polarized 3D: High-quality depth sensing with polarization cues

Achuta Kadambi, Vage Taamazyan, Boxin Shi, Ramesh Raskar • ICCV 2015

PDF