Safa C. Medin

I am a PhD student at the Electrical Engineering and Computer Science (EECS) department of Massachusetts Institute of Technology (MIT), supervised by Prof. Gregory W. Wornell. My research interests span the fields of computer vision and computational imaging, and I am currently focusing on problems in 3D vision and non-line-of-sight imaging.


  • August 2022 | Our paper, "Can Shadows Reveal Biometric Information?", is accepted to WACV2023! Paper available here.

  • May 2022 | I started my summer internship at Google AR in San Francisco, CA!

  • December 2021 | Our paper, "MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation", is accepted to AAAI2022! Paper available here.

  • September 2021 | I received my Master's degree from MIT EECS! Thesis available here.

  • July 2021 | Our paper, "Identity-Expression Ambiguity in 3D Morphable Face Models", is accepted to FG2021! Paper available here.


Face Image Manipulation

Recent advances in generative adversarial networks have led to remarkable achievements in face image synthesis. While recent methods have the ability to generate strikingly photorealistic face images, it is often difficult to manipulate the characteristics of the generated faces in a 3D-controllable and disentangled manner. In this project, our goal is to integrate a 3D face model into the photorealistic image generation process and achieve a fully disentangled face image manipulation pipeline that allows for extrapolating beyond the variations in the datasets.

Occluder-aided Non-Line-of-Sight Imaging

Non-line-of-sight imaging (NLOS) is the study of extracting information from the hidden scenes based on the visible scenes that are in our direct line-of-sight. A popular NLOS imaging setting, namely occluder-aided imaging, typically exploits occluding structure in the scenes to achieve this task. In this project, we aim to develop learning-based methods for a variety of occluder-aided imaging applications to achieve robust and reliable NLOS imaging systems.

Bernoulli Parameter Estimation

active imaging
Active imaging systems reconstruct an image of a scene using active illumination sources. In these systems, periodic illumination pulses sent from the source can either be absorbed by the scene or reflect back from it, depending on the reflectivities of the illuminated scene patches. Representing the probability of reflection from each patch as a Bernoulli parameter, the image acquisition process can be modeled as a problem of estimating arrays of Bernoulli parameters. In this setting, varying resources across multiple patches can yield significant improvements in acquisition efficiency. Motivated by this, we aim to develop adaptive acquisition strategies that achieve such performance improvements.


  • Safa C. Medin, Amir Weiss, Fr├ędo Durand, William T. Freeman, and Gregory W. Wornell, "Can Shadows Reveal Biometric Information?", in IEEE/CVF Winter Conference on Applications of Computer Vision, 2023. Available here.

  • Safa C. Medin, Bernhard Egger, Anoop Cherian, Ye Wang, Joshua B. Tenenbaum, Xiaoming Liu, and Tim K. Marks, "MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation", in 36th AAAI Conference on Artificial Intelligence, 2022. Available here.

  • Bernhard Egger, Skylar Sutherland, Safa C. Medin, and Joshua B. Tenenbaum, "Identity-Expression Ambiguity in 3D Morphable Face Models", in IEEE International Conference on Automatic Face and Gesture Recognition, 2021.
    Available here.

  • Safa C. Medin, "Learning-based Methods for Occluder-aided Non-Line-of-Sight Imaging", Master's Thesis, Massachusetts Institute of Technology, 2021. Available here.

  • Safa C. Medin, John Murray-Bruce, David Castañón, and Vivek K. Goyal, "Beyond Binomial and Negative Binomial: Adaptation in Bernoulli Parameter Estimation", in IEEE Transactions on Computational Imaging, vol. 5, no. 4, pp. 570-584, Dec. 2019. Available here.

  • Safa C. Medin, John Murray-Bruce, and Vivek K. Goyal, "Optimal Stopping Times for Estimating Bernoulli Parameters with Applications to Active Imaging", in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. Available here.