|
I am a second-year PhD student at UC San Diego working in Dr Ravi Ramamoorthi's group. I completed my undergraduate studies at UC Berkeley in Applied Mathematics and Computer Science. I was also part of Dr Ren Ng's group, which is a part of the Berkeley AI Research Group. My research interests include deep learning optimization, graphics, hardware acceleration and parallelization. My Berkeley alumnus website can be found here. Email / Resume / LinkedIn / GitHub / Google Scholar |
|
|
|
 
|
Nithin Raghavan*, Yan Xiao*, Kai-En Lin, Tiancheng Sun, Sai Bi, Zexiang Xu, Tzu-Mao Li, Ravi Ramamoorthi Computer Graphics Forum (Proc. EGSR), 2023 PRT-inspired hybrid neural-wavelet architectures trained on images can learn a scene's global illumination light transport tensor. Decoupling relighting from scene information as well as prediction in an orthonormal basis enable generalization to novel view and novel lighting conditions for many complex effects, such as rotating caustics. |
|
Matthew Tancik*, Pratul Srinivasan*, Ben Mildenhall*, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, Ren Ng NeurIPS, 2020 (Spotlight) project page / arXiv / code Mapping input coordinates with simple Fourier features before passing them to a fully-connected network enables the network to learn much higher-frequency functions. |
|
|
 
|
Modeling The Effect of Lateral Inhibition in the Retina on Color Perception
CS 294-164: A biologically-plausible model for fixational drift motion in the retina based on Anderson, et al. (2020) taking into account neuronal lateral inhibition is able to better reconstruct higher-contrast regions of input stimuli, and could potentially show more improvements with a well-chosen spatial prior |
|
On the Generalizability of Two-Layer ReLU-activated Neural Networks with a Fourier Feature Embedding
CS 294-220: Deriving generalizability bounds of binary coordinate-based MLPs with an input Fourier Feature encoding using Rademacher analysis and reproducing kernel Hilbert space (RKHS) theory. |
|
Statistics 153 Final Project
STAT 153: Predicting the future price of a stock using methods from time series analysis. |
|
|