Research Focus
I'm interested in computer vision, computational imaging and machine learning. Broadly, I wish
to harness a conjuction of newer hardware and smarter algorithms to tackle a variety of problems. My
undergraduate research focussed on developing deep learning techniques to recover high-quality
images from lensless cameras.
|
News
- (Aug 1st, 24) Our single-photon demo was recognized with the "best in show" award at SIGGRAPH E-Tech!
- (Jul 19th, 24) Demoing single-photon applications at SIGGRAPH. Say hi if you're at Denver next week!
- (Feb 26th, 24) One first-authored paper accepted at CVPR! See you in Seattle!
- (Jul 13th, 23) One first-authored paper accepted at ICCV as an oral presentation!
- (Mar 28th, 23) One paper accepted at SIGGRAPH!
- (Mar 6th, 22) One first-authored paper accepted at CVPR. First
paper of my PhD!
- (Mar 31st, 21) Our reproducibility work has been accepted for
publication at Rescience-C!
- (Mar 30th, 21) Gave a talk at the W&B Salon on our
reproducibility work.
- (Mar 26th, 21) Awarded UW CS summer RA-ship!
- (Feb 18th, 21) IITM featured a pop-sci style
article on our lensless work!
- (Jan 25th, 21) Joining UW Madison for grad school!
- (Oct 16th, 20) Our work on lensless imaging has been accepted
for
publication in IEEE TPAMI!
- (Oct 16th, 20) We placed 2nd in the ECCV Under
Display Camera Challenge
(POLED track). Paper
available
on arxiv.
- (Aug 1st, 20) Graduated from IIT Madras!
- (Apr 15th, 20) Accepted to PhD programmes at UW
Madison, CMU, USC, Rice University and
UCLA!
- (May 17th, 19) I will be interning at Prof. Ram
Nevatia's lab in USC till August
2019
|
|
A Live Demo of Single-Photon Imaging and Applications
Sacha Jungerman*,
Varun Sundar*,
Mohit Gupta.
SIGGRAPH Emerging Technologies 2024
* denotes equal contribution.
Best in show award
ACM page /
bibtex
A demonstration of single-photon imaging capabilities---including high-speed, high-dynamic range, and low-light vision---at SIGGRAPH's emerging technologies track.
|
|
Generalized Event Cameras
Varun Sundar*,
Matt Dutson*,
Andrei Ardelean,
Claudio Bruschini,
Edoardo Charbon,
Mohit Gupta.
CVPR 2024
* denotes equal contribution.
project page /
video /
bibtex
Single-photon cameras can not only emulate event cameras, but also facilitate a generalized space of intensity-preserving event cameras.
|
|
SoDaCam: Software-defined Cameras via Single-Photon Imaging
Varun Sundar,
Andrei Ardelean,
Tristan Swedish,
Claudio Bruschini,
Edoardo Charbon,
Mohit Gupta.
ICCV 2023 (Oral)
project page /
video /
bibtex
Photon-level software-defined cameras can emulate a diverse range of imaging modalities.
|
|
Seeing Photons in Color
Sizhuo Ma,
Varun Sundar,
Paul Mos,
Claudio Bruschini,
Edoardo Charbon,
Mohit Gupta.
SIGGRAPH 2023
project page /
video /
bibtex
Color filter and algorithm design for single-photon color imaging in low light.
|
|
Single-Photon Structured Light
Varun Sundar,
Sizhuo Ma,
Aswin Sankarnarayanan,
Mohit Gupta.
Computer Vision and Pattern Recognition (CVPR) 2022
project page /
arXiv /
video /
bibtex
Single-Photon Avalanche Diodes (SPADs) can be operated as extremely high-speed binary imagers and find a synergistic application in Structuered Light.
|
|
[Reproducibility Report]: Rigging the Lottery: Making All Tickets Winners
Varun Sundar,
Rajat Vadiraj Dwaraknath.
ML Reproducibility Challenge 2020, Rescience-C Journal
OpenReview /
arXiv /
YouTube /
W&B
Report /
bibtex
Reproducibility Report on the ICML 2020 paper "Rigging the Lottery: Making All Tickets Winners".
|
|
Deep Atrous Guided
Filter
for Image Restoration in Under Display Cameras
Varun Sundar*,
Sumanth Hegde*,
Divya K Raman,
Kaushik Mitra.
ECCV RLQ-TOD Workshop, 2020
* denotes equal contribution.
project page /
arXiv /
video /
bibtex
Guided Filters when incorporated in a deep network can efficiently recover severely degraded,
mega-pixel resolution images.
|
|
FlatNet: Towards Photorealistic Scene
Reconstruction from Lensless Measurements
Salman S. Khan*,
Varun Sundar*,
Vivek Boominathan,
Ashok Veeraraghavan,
Kaushik Mitra.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
* denotes equal contribution.
project page /
arXiv /
video /
bibtex
We propose a general learning based framework to recover photorealistic scenes from lensless
captures for both separable and non-separable forward models.
|
|