About Me

I am currently a PhD student at MIT CSAIL in the Computer Graphics group advised by Prof. Fredo Durand.

Presently, I focus on differentiable simulation methods, more specifically, on differentiable rendering and its applications to computer vision and perception. Other topics I'm familiar with/looking to work on include compilers for differentiable programming, real-time path tracing, synthetic image denoising, and physically-based modelling.

My previous experience include a 6-month research staff position at CMU (advised by Prof. Ioannis Gkioulekas and Prof. Anat Levin) and two consecutive summer internships at INRIA (advised by Prof. George Drettakis).

In my time-off, I like to travel, take pictures, and design websites. The end of this webpage has a few of my favourite pictures.

You can find a copy of my CV here!

Research Projects

Selected projects from 2013 through 2019

Parallel Algorithms


A performance-optimized CUDA path tracer that uses dynamic ray scheduling and 8-way BVH trees in order to make maximum use of the GPU's architecture. The algorithm used is based on a breadth-frist traversal where all the rays are advanced through the BVH one level at a time.

Thumbnail [200x250]
Physics-based Vision

Inverting generalised Global Illumination

A solution to the problems with shape-recovery methods. Uses a mitsuba shape-differentiable path tracer and a TensorFlow optimizer to obtain accurate reconstructions in the presence of interreflections and non-lambertian surfaces.

Thumbnail [200x250]
Deep Scene Representations

Action Conditional Projection Neural Networks

Similar to Action-Conditional Video Prediction, which predicts the next frame of an ATARI game given the user input, ACPNNs are designed to predict 2D and 3D environments where the output is based on perspective vision.

Thumbnail [200x250]
Deep Reinforcement Learning

Multi-task Reinforcement Learning

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We evaluate our method on a new set of environments and provide intuitive interpretation of our results.

Thumbnail [200x250]


A timeline of my academic education and internships

  • Carnegie Mellon University
  • Research Staff, Computer Graphics Group, RI
  • Pittsburgh, PA, United States of America
  • Currently working on shape reconstruction through differentiable rendering.
  • Dec 2018 - Current

  • Mobile 3D Graphics
  • Santa Clara, CA, United States of America
  • Worked on OpenGL Graphics Drivers
  • Improved internal GL testing suite efficiency
  • Contributed to Khronos' Vulkan Validation Layer
  • May 2018 - Aug 2018

  • GraphDeco Research Group, INRIA Sophia-Antipolis
  • Sophia-Antipolis, Provence-Alpes-Côte d'Azur, France
  • Under the supervision of Prof. George Drettakis, our team extended the paper Scalable InsideOut Rendering to handle thousands of input viewpoints using a streaming architecture and a spatial data structure. Paper currently in progress.
  • May 2017 - Aug 2017

  • GraphDeco Research Group, INRIA Sophia-Antipolis
  • Sophia-Antipolis, Provence-Alpes-Côte d'Azur, France
  • Worked under the mentorship of Prof. George Drettakis, to fix and enhance the pipeline of the popular algorithm Multi-view intrinsic images with an Application to Relighting which deals with decomposing the various components of lighting of an outdoor scene using images taken at different parts of the day
  • May 2016 - Aug 2016

  • Indian Institute of Technology Madras
  • Bachelor's Degree (BTech)
  • Chennai, TN, India
  • Joined the Computer Science and Engineering Department at IIT-Madras in Fall 2013
  • GPA: 9.35/10.0
  • Aug 2013 - Aug 2017


Pictures from around the world!