Scholar
Sudarshan Rajagopalan
Google Scholar ID: SGty2eUAAAAJ
Student at Johns Hopkins University
Citations & Impact
Citations
19
H-index
3
i10-index
0
Publications
9
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- September 2025: Intern at Dolby Laboratories (generative video models); 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 include 'RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration', 'GenDeg: Diffusion-Based Degradation Synthesis for Generalizable All-in-One Image Restoration', 'SINR: Sparsity Driven Compressed Implicit Neural Representations', 'Low-rank Adaptation-based All-Weather Removal for Autonomous Navigation', 'AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning', 'Remote Task-oriented Grasp Area Teaching By Non-Experts through Interactive Segmentation and Few-Shot Learning', and 'Spectrum-inspired Low-light Image Translation for Saliency Detection'.
Research Experience
- Currently a Fall intern at Dolby Laboratories working on generative video models.
Education
- Completed undergraduate studies at Madras Institute of Technology, Anna University; received DAAD WISE scholarship for an internship with Prof. Eckehard Steinbach at TUM, Germany; worked with Prof. Kaushik Mitra at the Computational Imaging Lab, IIT Madras on deep learning-based image restoration problems; currently a third-year PhD student in the Vision and Image Understanding (VIU) Lab at Johns Hopkins University, advised by Prof. Vishal Patel.
Background
- Research interests include computer vision, particularly the development of image and video restoration algorithms. Utilizes generative AI techniques such as autoregressive image generation, latent diffusion models, as well as advanced concepts like visual in-context learning and parameter-efficient fine-tuning (PEFT). Also interested in solving computer vision problems involving multimodal generation, vision-language models, and large language models (LLMs).
Miscellany
- Received DAAD WISE scholarship for an internship with Prof. Eckehard Steinbach at TUM, Germany.
