Gemmechu Hassena

Research Projects Talks Awards Service CV

Gemmechu Hassena

I am a CS PhD student at Cornell University working in the intersection of Machine Learning, Computer Vision and Graphics, advised by Prof. Bharath Hariharan and Prof. Steve Marschner. My research focuses on recovering the geometry and material properties of the 3D world directly from visual data in unconstrained capture settings. Prior to Cornell I earned my Bachelor's in Software Engineering from Addis Ababa University, Ethiopia. I have worked as a research intern at Ecole Polytechnique with Prof. Maks Ovsjanikov and at the University of Michigan with Prof. David Fouhey on computer vision, graphics and machine learning projects.

News

Aug 2025 Awarded Telluride Scholarship — 5 years full boarding and room
May 2025 Research Scientist Intern at Meta, hosted by Chris Sweeney and collaborating with Adam Harley and Michael Goesele on Dynamic Reconstruction project.
Jan 2025 Organized Computer vision and Graphics research Initiative in Ethiopia!
May 2024 Awarded “Exemplary Service Award for Early Career Graduate Students” and “Bowers CIS Distinguished Leadership in Service Award”
April 2024 Presented poster at NYC Computer Vision Day, NYU
Dec 2023 Gave a talk at DevFest Addis 2023
Dec 2023 Lightning talk at NYC vision workshop, Cornell Tech
Aug 2022 Started PhD at Cornell!
Mar 2022 Team lead in Product Management at A2SV/Eskalate
Oct 2021 Research intern at Ecole Polytechnique
Oct 2021 Graduated from AAU with Great distinction!
Jun 2021 Quantifying Bird Skeletons accepted at CVPR workshop [paper]
Apr 2021 Blog post on UMich AI website [blog]
May 2020 Research intern at University of Michigan
Dec 2019 Talk on Afro-FM radio about INSPIRE club & AI in Ethiopia conference
Nov 2019 Organized Twitter CEO Jack Dorsey’s visit to AAU [photo]
Nov 2019 Invited Tensorflow Speaker on DevFest Addis [website]
Oct 2019 Organized 1st AI in Ethiopia Conference [website]

...show all...

Research

ObjectCarver: Semi-automatic segmentation, reconstruction and separation of 3D objects

Gemmechu Hassena, Jonathan Moon, Ryan Fujii, Andrew Yuen, Noah Snavely, Steve Marschner, Bharath Hariharan

3DV 2025

Given multi-view images and point clicks in a single view, ObjectCarver generates a mask, propagates it to other views, reconstructs the 3D surface, and separates individual objects in the scene.

project page arXiv

Quantifying Bird Skeletons

Zhizhuo Zhou, Gemmechu Hassena, Brian C. Weeks, David F. Fouhey

CV4Animals Workshop @ CVPR 2021

We introduced a dataset and system for measuring skeletal traits from museum specimens, which speeds up skeleton measurement by 15x. This research helped ecologists study how global warming causes birds to shrink.

PDF BibTeX

Projects

Scene understanding using humans as a ruler

Gemmechu Hassena, Chris Rockwell, David Fouhey

AURA 2020

Monocular depth estimation using people's height as a reference to estimate depth and floor of a scene.

Video

Expanding Horizons: Visual Indeterminacy as A Vehicle For Inquiry and New Connections

Devi Parikh, Amal Alabdulkarim, Gemmechu Hassena, Oana Ignat, Jiasen Lu, Ryan Murdock

Collaboration 2021

Website

The adventure of rats

Gemmechu Hassena

Individual 2018

Developed a 3D game with Unity engine.

Others

What is your dog likelihood?

Gemmechu Hassena, Simret Araya, Bharath Hariharan

SIGBOVIK 2024

We train and evaluate a system to predict dog likelihood based on a human face using facial recognition models.

PDF

Talks

Nov 2024 Poster and 3MT Thesis competition, IVY Collective Symposium, Harvard
Jul 2024 Panelist Summer Success Symposium, Cornell
Jun 2024 Research Overview, SoNiC Cornell
Apr 2024 Lightning talk Grad Cohort for IDEALS, Minneapolis
Mar 2024 Research talk, hosted by Prof. Maks Ovsjanikov, Ecole Polytechnique
Mar 2024 Research talk, hosted by Prof. Abe Davis, Cornell Vision & Graphics Seminar
Dec 2023 3D for Everyone (co-presented with Milky Hassena), DevFest Addis
Dec 2023 Lightning presentation, NYC vision workshop, Cornell Tech
Oct 2023 African Undergraduate Research Adventure Panel, University Michigan
Jun 2023 McNair Scholar Panel, Cornell

Teaching

CS 4621 — Computer Graphics Practicum, Cornell Univeristy
CS 6670 — Graduate Computer Vision, Cornell Univeristy
CS 4780 — Introduction to Machine Learning, Cornell Univeristy

Awards

Telluride Scholarship — Full 5-year fellowship with room & board, Telluride Association (2025)
Exemplary Service Award — Cornell University (2024)
Distinguished Leadership in Service Award — Cornell Bowers CIS (2024)

Service

Wild3D workshop, ECCV — Technical paper reviewer 2024
Summer Geometry Initiative - MIT — Social hour Chair, 2023 and 2024
SoNiC - Cornell University — TA, 2024
A2SV - Africa to Silicon Valley — Mentor/student, 2019-2022
INSPIRE - Addis Ababa University — President, 2019–2020