Sudarshan Rajagopalan

I am a second-year PhD student in the Vision and Image Understanding (VIU) Lab at Johns Hopkins University, advised by Prof. Vishal Patel. I work in the area of computer vision, focusing on developing image restoration algorithms with enhanced real-world applicability. My research leverages generative AI techniques such as autoregressive image generation and latent diffusion models, as well as other advanced concepts like visual in-context learning and parameter-efficient fine-tuning (PEFT), to enhance restoration performance. I am also keenly interested in solving computer vision problems involving multimodal generation, vision-language models, and large language models (LLMs).

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. I also worked with Prof. Kaushik Mitra at the Computational Imaging Lab, IIT Madras, on deep learning-based image restoration problems.

CV  /  Email  /  GitHub  /  Google Scholar  /  LinkedIn

News

February, 2025: Two Papers accepted at CVPR 2025.

January, 2025: One Paper accepted at ICRA 2025.

December, 2024: One Paper accepted at AAAI 2025.

August, 2023: Joined VIU Lab, JHU as a PhD student.

December, 2022: One Paper accepted at AAAI Workshop 2023.

November, 2022: One Paper accepted at ICVGIP 2022 (spotlight).

Publications

RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration

Sudarshan Rajagopalan, Kartik Narayan, Vishal M. Patel

GenDeg: Diffusion-Based Degradation Synthesis for Generalizable All-in-One Image Restoration

Sudarshan Rajagopalan, Nithin Gopalakrishnan Nair, Jay N. Paranjape, Vishal M. Patel

SINR: Sparsity Driven Compressed Implicit Neural Representations

Dhananjaya Jayasundara, Sudarshan Rajagopalan, Don Yasiru Lakshan Ranasinghe, Trac Tran, Vishal M. Patel

Low-rank Adaptation-based All-Weather Removal for Autonomous Navigation

Sudarshan Rajagopalan, Vishal M. Patel

AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning

Sudarshan Rajagopalan, Vishal M. Patel

Remote Task-oriented Grasp Area Teaching By Non-Experts through Interactive Segmentation and Few-Shot Learning

Furkan Kaynar*, Sudarshan Rajagopalan*, Shaobo Zhou, Eckehard Steinbach

Spectrum-inspired Low-light Image Translation for Saliency Detection

Kitty Varghese, Sudarshan Rajagopalan, Mohit Lamba, Kaushik Mitra

Design and source code from Jon Barron's website