About me

About me ๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ

I'm Mukul Khanna, a research fellow at the Robotics Research Center, IIIT Hyderabad, where I work on the intersection of computer vision and deep learning, advised by Prof. K. Madhava Krishna. Previously, I was a research intern at IIT Gandhinagar, advised by Prof. Shanmuganathan Raman, where I worked on HDR image and video processing using deep learning.

I was a Google Summer of Code 2019 student at Open Robotics, where I worked on creating a documentation index for the Gazebo simulation environment.

I host a data science podcast - Deep Neural Notebooks, where I interview researchers about their research, insights and their journeys. I'm also interested in the ideas of knowledge management and have taken to Youtube to share my learnings on the same. And here is some photography & art that I've dabbled with in the last year.

Contact: <firstname> 18 <lastname> ยท at ยท gmail.com

Links: ย CV ย / ย Github ย / ย Linkedin ย / ย Twitter

Experience

Research Fellow - Robotics Research Center, IIIT Hyderabad ๐Ÿค–Jan '20 - present

Webp.net-resizeimage--4-

Advisor: Dr. K. Madhava Krishna
Working on building plane segmentation and surface normal estimation for 3D reconstruction from drone-view images using deep learning and geometrical methods.

Technical Writer & Editor - Scout APM โœ๐ŸฝOct '19 - present
Advisor: Marty Johnson
  • Writing web development articles around Python, Node.js, PHP and Ruby for ScoutAPM's blog. Published articles can be found here.
Research Intern - IIT Gandhinagar ๐Ÿ•ต๐Ÿปโ€โ™‚๏ธ Feb '19 - Jan '20

Webp.net-resizeimage--3-

Advisor: Dr. Shanmuganathan Raman

  • Worked on HDR image reconstruction from single exposure LDR image using Deep Learning and Deep Weakly-Supervised High Speed HDR Video Generation.
    project page / code / paper

  • Worked on HDRSloMo: Deep Weakly-Supervised High Speed HDR Video Generation (to be submitted). [video]

Google Summer of Code 2019 - Open Robotics ๐Ÿค–May '19 - Sep '19
Advisor: Jose Luis Rivero
  • Created a documentation index and entry suggestion-tool for open-source robotic simulation software Gazebo.
Software Dev Intern - Remedico ๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ปJul '19 - Sep '19
  • Worked on updates in the Python and Ruby based back-end systems of multiple dashboard apps for doctors patients. [website]
Software Intern - Tata Consultancy Services (TCS) Digital ๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ปJan '19 - Apr '19
Advisor: Snehal Khole, Debkumar Maiti
  • Built a prototype of an Airline Helpdesk AI chatbot for getting flight details, booking and managing trips using a hybrid mobile application with speech support.
Software Team - SRM Autonomous Underwater Vehicle ๐ŸšขSep '17 - May '19

image

Advisor: Dr.Annapurani Panaiyappan K.
  • Developed the software stack and image processing modules for the vehicle using ROS (Robotic Operating System). [code]
  • Developed an underwater simulation environment using ROS and Unity-3D to test vehicle performance. [Project page]
    (Oral presentation at IEEE-OES UT-19, Kaohsiung)
Web Developer - Skylim Infotech ๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ปJul '17 - Oct '18
Advisor: Baraneedharan Karthikeyan, Dr. Revathi Venkataraman
  • Worked on developing for a CRM Ticketing system that provides a platform for enterprises to solve customer grievances.

Publications

Multi-view Planarity Constraints for Skyline Estimation from UAV images ๐Ÿข

Ayyappa S. Thatavarthy, Tanu Sharma, Harshit Sankhla, Mukul Khanna, K. Madhava Krishna
VISAPP 2021, 16th International Conference on Computer Vision Theory and Applications

FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network ๐ŸŒ‰

image

Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman
2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
[paper] / project page, code / slides

URSim: Open Source Simulator for Unmanned Underwater Vehicles using ROS & Unity3D ๐Ÿšข

Screenshot-2020-10-24-at-7.59.26-AM-copy-2

Pushkal Katara, Mukul Khanna, Harshit Nagar, Annapurani Panaiyappan
IEEE OES - Underwater Technology 2019, Kaohsiung (UT19)
paper / project page, code / slides

Projects

Embodied Question Answering Baseline in Habitat Lab ๐Ÿค–[open source]

ezgif com-gif-maker (3)

The aim is to implement an Embodied Question Answering Baseline in Habitat-lab, a modular high-level framework for end-to-end development in embodied AI.

Habitat Lab: https://github.com/facebookresearch/habitat-lab

More info about project: #374
Merged Pull Requests: #430 , #482
VQA baseline implementation [merged]: #487
NAV PACMAN baseline implementation [merged]: #539

FHDR: Feedback Network for Single Image HDR Image Reconstruction ๐ŸŒ‰[open source]

image

PyTorch Implementation of our Global SIP 2019 Paper FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network

code / paper

Gazebo Documentation Index ๐Ÿ—‚[open source]

ezgif com-gif-maker

The aim of this project is to bring all of Gazeboโ€™s learning material under one webpage in the form of a documentation index that contains links to the content where the respective information is hosted.

project / documentation

URSim: Underwater Simulation Framework using ROS and Unity ๐Ÿšข[open source]

Screenshot-2020-10-24-at-7.59.26-AM-copy-2

An open source underwater 3D simulation framework for Unmanned Underwater Vehicles (UUVs) developed using Robotics Operating System (ROS) and real-time 3D game engine Unity.

code / docs / paper

SRM Autonomous Underwater Vehicle ๐Ÿคฟ[open source]

image

SRM AUV is SRM IST's Autonomous Underwater Vehicle project, founded in 2013. The following is the link to the code of the vehicle.

code

P5.js visualizations ๐ŸŽˆ[open source]

example

Visualizing algorithms, sequences, animations and some games using P5.js

see them here / code

Great! You've successfully subscribed.
Great! Next, complete checkout for full access.
Welcome back! You've successfully signed in.
Success! Your account is fully activated, you now have access to all content.