Iβm an ML Engineer at Waymo. Previously, I was an MS student at Georgia Tech advised by Prof. Dhruv Batra, working on computer vision and embodied AI research. I was also an ML intern with Appleβs ο£Ώ Vision Products Group over spring and summer of 2024, and before that have had the privilege of working closely with Prof. Manolis Savva and Prof. Angel Chang at Simon Fraser University.
In a distant past, I have also had the privilege of interning at the Robotics Research Center at IIIT Hyderabad, advised by Prof. K. Madhava Krishna and at IIT Gandhinagar, advised by Prof. Shanmuga Raman.
On the side, I dabbled with hosting the Deep Neural Notebooks podcast, where I interviewed academics and scientists about their research, insights and journeys. Likewise, I also managed the Humans of AI podcast hosted by Devi Parikh and Dhruv Batra.
news
Jan 2025
Joined Waymo as an ML Engineer in the Perception Org.
Surface normal estimation is an essential component of several computer and robot vision pipelines. While this problem has been extensively studied, most approaches are geared towards indoor scenes and often rely on multiple modalities (depth, multiple views) for accurate estimation of normal maps. Outdoor scenes pose a greater challenge as they exhibit significant lighting variation, often contain occluders, and structures like building facades are often ridden with numerous windows and protrusions. Conventional supervised learning schemes excel in indoor scenes, but do not exhibit competitive performance when trained and deployed in outdoor environments. Furthermore, they involve complex network architectures and require many more trainable parameters. To tackle these challenges, we present an adversarial learning scheme that regularizes the output normal maps from a neural network to appear more realistic, by using a small number of precisely annotated examples. Our method presents a lightweight and simpler architecture, while improving performance by at least 1.5x across most metrics. We evaluate our approaches against the state-of-the-art on normal map estimation, on a synthetic and a real outdoor dataset, and observe significant performance enhancements.
FHDR
FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network πΈ
High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning. Various feed-forward Convolutional Neural Networks (CNNs) have been proposed for learning LDR to HDR representations. To better utilize the power of CNNs, we exploit the idea of feedback, where the initial low level features are guided by the high level features using a hidden state of a Recurrent Neural Network. Unlike a single forward pass in a conventional feed-forward network, the reconstruction from LDR to HDR in a feedback network is learned over multiple iterations. This enables us to create a coarse-to-fine representation, leading to an improved reconstruction at every iteration. Various advantages over standard feed-forward networks include early reconstruction ability and better reconstruction quality with fewer network parameters. We design a dense feedback block and propose an end-to-end feedback network-FHDR for HDR image generation from a single exposure LDR image. Qualitative and quantitative evaluations show the superiority of our approach over the state-of-the-art methods.
URSIM
Open Source Simulator for Unmanned Underwater Vehicles using ROS and Unity3D π
Pushkal Katara,
Mukul Khanna,
Harshit Nagar,
and A. Panaiyappan
The paper presents URSim: an open source 3D underwater simulation framework for Unmanned Underwater Vehicles (UUVs) developed using Robotics Operating System (ROS) and a real-time game engine called Unity3D. Simulation systems like these enable to implement, test, study and analyze complex systems while minimizing cost and disruption to the environment. URSim provides the user an intuitive way to simulate underwater vehicles and robots. It is capable of simulating feedback control systems, dynamic model, underwater vision and mission planning for underwater vehicles and robots. The simulation provides support for underwater sensor modules, underwater physics, collision kinematics and is highly configurable to simulate a realistic underwater environment. The software architecture is adaptive to algorithms for control systems, image processing, navigation and manipulation.
DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction πΈInternational Conference on Pattern Recognition (ICPR) 2022
