Ekta Prashnani
Ph.D. Candidate (Computer Vision)
University of California
Santa Barbara, CA

ekta at ece dot ucsb dot edu
[GitHub] [Google Scholar] [CV]

I am advised by Prof. Pradeep Sen. My current research focuses on enforcing perceptual consistency in algorithms that evaluate error/quality of images and applications of such a metric. A recent publication at CVPR2018 provides more details. I am also interested in attention modeling, gaze prediction, and 3D computer vision.

My time in grad school is split between my own research and providing technical mentorship (which I thoroughly enjoy!) to seniors for their capstone projects on computer vision and machine learning. I also enjoy running long distances, painting and taking pictures.


Updates
Jun, 2018: Our CVPR2018 paper about a new perceptual image-error metric (PieAPPv0.1) and the associated source code and trained model is now available online! Also, more information can be found on the project webpage.
May, 2018: Outstanding Teaching Assistant award by the ECE department at UCSB.
Apr, 2018: Google travel grant for CVPR2018.
Feb, 2018: Our paper "PieAPP: Perceptual Image-Error Assessment through Pairwise Preference" is accepted to CVPR 2018.. Code, trained models, and paper coming online soon!
Feb, 2018: Our patent on Single Image Rectification (filed for the work I did during my internship at Ricoh Innovations) is granted!
Oct, 2017: AI Grant fellowship for developing a perceptually-consistent image error metric.

Publications
E. Prashnani*, H. Cai*, Y. Mostofi and P. Sen, "PieAPP: Perceptual Image-Error Assessment through Pairwise Preference," Computer Vision and Pattern Recognition, 2018.
[project webpage] [paper] [supplementary] [source code] [.exe]

E. Prashnani, M. Moorkami, D. Vaquero and P. Sen, "A Phase-Based Approach for Animating Images Using Video Examples," Computer Graphics Forum, August 2016, Volume 36, Issue 6.
[paper] [video results]
*joint first authors

Teaching
Technical Mentorship for EE Capstone (2017-2018)

Provided technical mentorship to seniors on their EE Capstone projects (total five capstone projects).
I worked very closely with the capstone team working on medical image recognition for arthroscopic images (sponsored by Arthrex). The team (left to right: Jonathan Huynh, Phanitta Chomsinsap, Jacob Kurtz and Alae Amara) was selected to present their work at the Engineering Design Expo, 2018, at UCSB.

Research Mentor for High School Students (July 2017)

In the Summer of 2017, I had the opportunity to mentor four exceptional high school students (left to right in first picture: Sohini Kar, Jungwoo Park, Joshua Doolan, James Wang) as a part of the Summer Research Mentorship Program at UCSB.
I spent the first few weeks of the program teaching relevant concepts of computer vision and machine learning to these students (they followed along easily - the age for brilliance keeps getting younger!). The students spent the latter half of the program working on the research tasks I designed for them in applying deep learning to object detection (for Sohini and Jungwoo) and image restoration (for Joshua and James).

Technical Mentorship for EE Capstone (2016-2017)

Provided technical mentorship to seniors on their EE Capstone projects (total six capstone projects). I worked very closely with the capstone team working on deep-learning-based image super-resolution (sponsored by Flir).
The team (left to right: Julian Castro, Connor Northend, Jose Jimenez) ended up winning the award for the Best Technical Capstone Project!


I can also be found on: [LinkedIn] [Github] [Google Scholar] [Flickr] Twitter] [Behance]