Sudarshan Rajagopalan

I am a final-year PhD student in the Vision and Image Understanding (VIU) Lab at Johns Hopkins University, advised by Prof. Vishal M. Patel.

I work on generative models for vision, with an emphasis on adapting and leveraging them for real-world image and video restoration. My research spans diffusion and autoregressive models, as well as generative transport methods such as Schrödinger bridges. I am broadly interested in large-scale image and video generation, multimodal and omni-modal models, and post-training of generative models.

I am currently a Research Intern with the Computational Imaging Team at Google, Mountain View, working on generative models for synthetic data generation from unpaired data. Previously, I was a Research Intern at Dolby Laboratories, where I worked on large-scale video diffusion models for video enhancement with Dr. Tsung-Wei Huang and Dr. Shiv Gehlot.

I completed my undergraduate studies at the Madras Institute of Technology, Anna University. I received the DAAD WISE scholarship for an internship with Prof. Eckehard Steinbach at TUM, Germany, and worked with Prof. Kaushik Mitra at the Computational Imaging Lab, IIT Madras, on deep learning-based image restoration.

I am seeking full-time opportunities for early 2027.