Nithin Gopalakrishnan Nair

Ph.D. Student at Johns Hopkins University

SmallSize.png

I am a third year PhD student in the Department of Electrical and Computer Engineering at VIU Lab , Johns Hopkins University. I am advised by Dr. Vishal M Patel.

I work on problems in Computer Vision. My research areas include Face recognition and Deep Generative Modelling with a special emphasis on Plug and Play models and efficient architectures for generation, enabling training and inference of generative models on low compute resources.

Prior to joining JHU, I obtained my Bachelor’s and Master’s dual degree (B.Tech& M.Tech) in Electrical Engineering from Indian Institute of Technology, Madras. At IIT Madras, I worked with Dr AN Rajagopalan at the IPCV Lab, on image reconstruction. In my free time, I enjoy running and hiking.

I am looking for a research position in industry. Please reach out if you think I could be a good fit!

News

Jul 2024 Our work MaxFusion is accepted at ECCV 2024. Maxfusion enables training free multimodal spatial conditioning in text to image diffusion models.
Apr 2024 I started my summer internship at Nvidia Research.
Jul 2023 Our work Steered Diffusion is accepted at ICCV 2023. Steered diffusion enables zero-shot conditional sampling using pre-trained unconditional diffusion models.
May 2023 I started my summer internship at Adobe Seattle on Diffusion based Image editing.
Feb 2023 Our work Unite and Conquer is accepted at CVPR 2023. Unite and Conquer enables plug and play multimodal generation using diffusion models.

Selected Publications

  1. maxfusion.png
    MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models
    Nithin Gopalakrishnan Nair, Jeya Maria Jose Valanarasu, and Vishal M Patel
    arXiv preprint arXiv:2404.09977, 2024
  2. steered.png
    Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
    Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit, Ye Wang, Toshiaki Koike-Akino, Vishal M. Patel, and Tim K. Marks
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
  3. multi.png
    Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models
    Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, and Vishal M Patel
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2023
  4. binoising.png
    Diffuse-Denoise-Count: Accurate Crowd-Counting with Diffusion Models
    Yasiru Ranasinghe, Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, and Vishal M Patel
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Mar 2024