ShahRukh Athar

ShahRukh Athar

Member of Technical Staff at Mirage

Former Ph.D. Student, Department of Computer Science
Stony Brook University

CV / Google Scholar / Email

I am a Member of Technical Staff at Mirage. Before that, I was a Ph.D. student at Stony Brook University working under the supervision of Prof. Dimitris Samaras. My research interests lie in computer vision and machine learning. Prior to joining SBU, I did my Masters in Data Science at Skoltech under the supervision of Prof. Victor Lempitsky.

Publications

Seeing Voices

Seeing Voices: Generating A-Roll Video from Audio with Mirage

Aditi Sundararaman, Amogh Adishesha, Andrew Jaegle, Dan Bigioi, Hyoung-Kyu Song, Jon Kyl, Justin Mao, Kevin Lan, Mojtaba Komeili, ShahRukh Athar, Sheila Babayan, Stanislau Beliasau, William Buchwalter

Author list sorted by first name

arXiv preprint arXiv:2506.08279, 2025

Paper arXiv Blog Research Page
Bridging the Gap

Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture

ShahRukh Athar, Shunsuke Saito, Zhengyu Yang, Stanislav Pidhorskyi and Chen Cao

European Conference on Computer Vision (ECCV), 2024, Oral

Paper arXiv Project Page
CoDyNeRF

Controllable Dynamic Appearance for Neural 3D Portraits

ShahRukh Athar, Zhixin Shu, Zexiang Xu, Fujun Luan, Sai Bi, Kalyan Sunkavalli, Dimitris Samaras

International Conference on 3D Vision (3DV), 2024

Paper arXiv Project Page
LipNeRF

LipNeRF: What is the right feature space to lip-sync a NeRF?

Aggelina Chatziagapi, ShahRukh Athar, Abhinav Jain, Rohith MV, Vimal Bhat, Dimitris Samaras

17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023)

Paper Project Page
RigNeRF

RigNeRF: Fully Controllable Neural 3D Portraits

ShahRukh Athar, Zexiang Xu, Kalyan Sunkavalli, Eli Shechtman, Zhixin Shu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Paper arXiv Project Page
SIDER

SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery

Aggelina Chatziagapi*, ShahRukh Athar*, Francesc Moreno-Noguer, Dimitris Samaras

International Conference on 3D Vision (3DV), 2021

Paper Project Page
FLAME-in-NeRF

FLAME-in-NeRF: Neural control of Radiance Fields for Free View Face Animation

ShahRukh Athar, Zhixin Shu, Dimitris Samaras

17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023)

Paper Project Page
FaceDet3D

FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction

ShahRukh Athar, Albert Pumarola, Francesc Moreno-Noguer, Dimitris Samaras

arXiv:2012.07999

Paper Project Page
Variational Transfer Learning

Variational Transfer Learning for Fine-grained Few-shot Visual Recognition

Jingyi Xu, Hieu Le, Mingzhen Huang, ShahRukh Athar, Dimitris Samaras

ICCV 2021

Paper
Self-Supervised Deformation

Self-Supervised Deformation Modeling for Facial Expression Editing

ShahRukh Athar, Zhixin Shu, Dimitris Samaras

15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)

Paper
Latent Convolutional Models

Latent Convolutional Models

ShahRukh Athar, Evgeny Burnaev, Victor Lempitsky

International Conference on Learning Representations (ICLR), 2019

Paper Project Page Code
Weakly Supervised Fluid Localization

Weakly supervised fluid filled region localization in retinal OCT scans

ShahRukh Athar, Abhishek Vahadane, Ameya Joshi, Tathagato Rai Dastidar

International Symposium on Biomedical Imaging (ISBI), 2018

Paper