I am a PhD student at the Laboratory for Image and Video Engineering at UT Austin, where I have also been serving as the Assistant Director since 2020. My advisor is Professor Alan Bovik. My research interests include video quality assessment, deep learning, and video processing. I received my B.Tech. from IIT Kharagpur, where I was awarded the Nilanjan Ganguly Memorial Award for the best undergraduate thesis and had the 3rd highest GPA in my graduating batch. My recent work has focused on video quality assessment for livestreamed high-motion videos, and I am currently working on quality assessment for HDR video. My work is sponsored by Amazon Prime Video.
Being an academic is my vocation, and one that I enjoy immensely. I play the keyboard and the guitar occasionally. I love reading theology, history, philosophy, listening to music that stirs the soul, and getting to travel and experience different cultures and cuisines .
PhD in ECE, 2019 -
B.Tech in ECE, 2019
We propose a new prototype model for no-reference video quality assessment (VQA) based on the natural statistics of space-time chips of videos. Space-time chips (ST-chips) are a new, quality-aware feature space which we define as space-time localized cuts of video data in directions that are determined by the local motion flow. We use parametrized distribution fits to the bandpass histograms of space-time chips to characterize quality, and show that the parameters from these models are affected by distortion and can hence be used to objectively predict the quality of videos. Our prototype method, which we call ChipQA-0, is agnostic to the types of distortion affecting the video, and is based on identifying and quantifying deviations from the expected statistics of natural, undistorted ST-chips in order to predict video quality. We train and test our resulting model on several large VQA databases and show that our model achieves high correlation against human judgments of video quality and is competitive with state-of-the-art models.
We present a method to restore a clear image from a haze-affected image using a Wasserstein generative adversarial network. As the problem is ill-conditioned, previous methods have required a prior on natural images or multiple images of the same scene. We train a generative adversarial network to learn the probability distribution of clear images conditioned on the haze-affected images using the Wasserstein loss function, using a gradient penalty to enforce the Lipschitz constraint. The method is data-adaptive, end-to-end, and requires no further processing or tuning of parameters. We also incorporate the use of a texturebased loss metric and the L1 loss to improve results, and show that our results are better than the current state-of-the-art.
Developed a new feature space and algorithm for video quality.
Proposed a novel application of CWGANs.
Implemented and optimized a fog-removal algorithm on an FPGA.