Akshaya Athwale

I'm Akshaya Athwale, a Ph.D. student at Université Laval. I have the privilege of working under the guidance of Prof. Jean-François Lalonde and Ola Ahmad. My research focuses on geometric deep learning and developing netowkrs to understnad and reason on distortions in wide-angle images. During my Ph.D. journey, I had the valuable opportunity to intern at Thales Digital Solutions, where I worked closely with Ola Ahmad. Before joining Université Laval, I did a research assistantship at Aalto University under the supervision of Alexander Ilin, where I worked on physics-informed neural networks. I completed my Bachelor's degree in Mathematics and Computing from IIT(ISM) Dhanbad.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

I'm interested in geometric deep learning, wide angle images, and computer vision. Currently, I have focused my research on developing networks for understanding distortion in wide-angle images and reasoning on them without undistorting them. Here, you can find a list of my papers.

DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture
Akshaya Athwale, Ichrak Shili, Émile Bergeron, Ola Ahmad, Jean-François Lalonde
WACV, 2025
project page / arXiv

DarSwin: Distortion Aware Radial Swin Transformer
Akshaya Athwale, Arman Afrasiyabi, Justin Lagüe, Ichrak Shili, Ola Ahmad, Jean-François Lalonde
ICCV, 2023
project page / video / arXiv

FunSyn-Net: enhanced residual variational auto-encoder and image-to-image translation network for fundus image synthesis
Sourya Sengupta, Akshaya Athwale, Tanmay Gulati, John Zelek, Vasudevan Lakshminarayanan,
SPIE Medical Imaging, 2020
paper page

Deep Sky Modeling for Single Image Outdoor Lighting Estimation
Yannick Hold-Geoffroy, Akshaya Athwale, Jean-François Lalonde
CVPR, 2019   (Oral Presentation)
project page / arXiv


Design and source code from Jon Barron's website.