Semih Günel

I am a third year doctoral candidate at EPFL, Lausanne, Switzerland. I am doing a joint Ph.D. at Computer Vision Lab and Neuroengineering Lab. I'm interested in computer vision, machine learning, modeling time series, behavioral neuroscience and ethology.

Before that, I obtained my B.Sc. from Computer Science at Bilkent University, Ankara, Turkey.

My offices are at BC 301 and AI 1125.

Email  /  Google Scholar  /  Linkedin  /  Twitter  /  Github

profile photo
Publications
Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
Paper  /  Poster  /  Video  /  Code  /  Bibtex
Siyuan Li, Semih Günel, Mirela Ostrek, Pavan Ramdya, Pascal Fua, Helge Rhodin
CVPR, 2020

Performing unsupervised pose-estimation on lab animals using rough animal models.

DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila
Paper  /  Video  /  Dataset  /  Code  /  Bibtex
Semih Günel, Helge Rhodin, Daniel Morales, João Campagnolo, Pavan Ramdya, Pascal Fua
eLife, 2019

Multi-view motion capture system for model organism Drosophila Melonagaster.

On Press:
Gravity as a Reference for Estimating a Person's Height from Video
Paper  /  Video  /  Bibtex
Didier Bieler, Semih Günel, Pascal Fua, Helge Rhodin
ICCV, 2019

Monocular scale/height estimation on videos using free-fall motion.

What Face and Body Shapes Tell Us About Height
Paper  /  Dataset  /  Bibtex
Semih Günel, Helge Rhodin, Pascal Fua
ICCVW, 2019  

Monocular scale/height estimation using single images. Monocular human pose dataset with 12,000 person with known height. 1e6 images with a person with known height.

Projects
If you are a bachelor/master student in EPFL, and want to work on the following projects for credits, you can contact me.
Teaching
Machine Learning TA, 2019 Fall

Computer Vision TA, 2018, 2019 Spring

Foundations of Software (Functional Programming) TA, 2018 Fall

Convex Optimization TA, 2017 Spring

JB's HTML template.