Akshay Paruchuri

I'm a 3rd-year PhD student in the Department of Computer Science at UNC Chapel Hill. I'm advised by Roni Sengupta. I'm currently a student researcher on the Consumer Health Research Team (CHRT) at Google in Seattle, WA. At Google, I work with Xin Liu and Daniel McDuff on large language models (LLMs) and personalization in the context of consumer health. I'm generally interested in research at the intersection of computer vision, computer graphics, machine learning, and healthcare. Despite being especially motivated by healthcare applications, I'm also interested in and occasionally work on projects involving augmented reality, virtual reality, and robotics.

In the past, I've worked at Kitware as an intern and on Nike's Advanced Innovation Team as both an intern and a full-time engineer. I completed my undergraduate education in the Department of Electrical and Computer Engineering at NC State University.

I'm happy to chat about research, new opportunities, and life in general with just about anyone. Feel free to contact me via email or Twitter!

Email / CV / Google Scholar / Twitter / Github

Research and Publications

To see a full, most recent list of my publications, please refer to my Google Scholar.

* denotes equal contribution for joint authorship or advising

	Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos Akshay Paruchuri, Samuel Ehrenstein, Shuxian Wang, Inbar Fried, Stephen M. Pizer, Marc Niethammer, Roni Sengupta arXiv 2024 [PDF][Project Page][arXiv][Code] We model near-field lighting, emitted by the endoscope and reflected by the surface, as Per-Pixel Shading (PPS). We use PPS features to perform depth refinement (PPSNet) on clinical data using teacher-student transfer learning and a PPS-informed self-supervision, ultimately achieving state-of-the-art results on colonoscopy data.
	Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement Akshay Paruchuri, Xin Liu, Yulu Pan, Shwetak Patel, Daniel McDuff, Roni Sengupta WACV 2024 Oral, Top 2.6% (53 of 2042 submissions) [PDF][Project Page][arXiv][Code] Neural Motion Transfer serves as an effective data augmentation technique for PPG signal estimation from facial videos. We devise the best strategy to augment publicly available datasets with motion augmentation, improving up to 79% in inter-dataset testing involving five benchmark datasets and 47% over existing results using SOTA methods on PURE.
	rPPG-Toolbox: Deep Remote PPG Toolbox Xin Liu, Akshay Paruchuri, Girish Narayanswamy, Xiaoyu Zhang, Jiankai Tang, Yuzhe Zhang, Yunato Wang, Roni Sengupta, Shwetak Patel, Daniel McDuff NeurIPS 2023 Datasets and Benchmarks Track [PDF][arXiv][Code] We present a comprehensive toolbox, rPPG-Toolbox, that contains unsupervised and supervised rPPG models with support for public benchmark datasets, data augmentation, and systematic evaluation.
	Reconstruction of Human Body Pose and Appearance Using Body-Worn IMUs and a Nearby Camera View for Collaborative Egocentric Telepresence Qian Zhang, Akshay Paruchuri, YoungWoon Cha, Jia-Bin Huang, Jade Kandel, Howard Jiang, Adrian Ilie, Andrei State, Danielle Szafir, Daniel Szafir, Henry Fuchs 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) [IEEE Xplore] We present a collaborative approach to 3D reconstruction that combines a set of IMUs worn by a target person with an external view from another nearby person wearing an AR headset, used for estimating the target person's body pose and reconstructing their appearance, respectively.

Miscellaneous

In my free time these days, I enjoy exploring the world with my partner, finding ways to stay physically active, reading, and playing the occasional computer game (games like DotA 2 are my go-to). I recently have been trying to get into running. Maybe I'll do a marathon one day!

A quote that recently inspired me comes from a speech by Theodore Roosevelt (former President of the United States) titled "Citizenship in a Republic". It stirs me in a similar fashion as Max Ehrmann's Desiderata. The quote is as follows:

It is not the critic who counts; not the man who points out how the strong man stumbles, or where the doer of deeds could have done them better. The credit belongs to the man who is actually in the arena, whose face is marred by dust and sweat and blood; who strives valiantly; who errs, who comes short again and again, because there is no effort without error and shortcoming; but who does actually strive to do the deeds; who knows the great enthusiasms, the great devotions; who spends himself in a worthy cause; who at the best knows in the end the triumph of high achievement, and who at the worst, if he fails, at least fails while daring greatly, so that his place shall never be with those cold and timid souls who neither know victory nor defeat.

You can read the full speech here.

Website Credits to Xin Liu (source code) and Jon Barron (source code)