Rahul Dey

PhD Student
Google Scholar

Hi! I am a third-year Graduate Student in the Computer Science and Engineering Department at Michigan State University pursuing my Ph.D. degree under the supervision of Dr. Vishnu Boddeti. My research interests lie specifically in Generative Models and Object Alignment. Recently, our paper RankGAN: A Maximum Margin Ranking GAN for Generating Faces won the Best Student Paper Award at the ACCV 2018. I am also associated with the Connected and Autonomous Vehicles (CANVAS) project at MSU directed by Dr. Hayder Radha, working on the alignment of vehicles in the presence of occlusion.

I received my bachelor’s and master’s (dual) degrees from the Electronics and Electrical Communication Engineering Department at the Indian Institute of Technology, Kharagpur in 2013. I have one year of work experience as a Research and Development Engineer and two years as a Software Engineer. I have a background in areas such as Signal Processing, Computer Vision, Machine Learning, Image Processing, and Multimedia Signal Processing and Compression. I am also a hobbyist photographer, and guitarist, and love travel and music.


CoLa-SDF: Controllable Latent StyleSDF for Disentangled 3D Face Generation

Generating Diverse 3D Reconstructions from a Single Occluded Face Image

3DFaceFill: An Analysis-By-Synthesis Approach to Face Completion

RankGAN: A Maximum Margin Ranking GAN for Generating Faces


Do explicit 3D priors improve face inpainting? We present 3DFaceFill!