Moneish Kumar

I am a Masters in Computer Vision student at the Robotics Institute, Carnegie Mellon University, where I am advised by Prof. Shubham Tulsiani. I am currently working on Sparse-View 3D Reconstruction.

Prior to joining CMU, I worked as a Reasearch Engineer at Samsung Research Institute - Banglore. I worked on developing a low-latency, low-footprint object detection and recognition framework for mobile devices.

Before that, I completed my undergraduation at IIIT - Hyderabd, advised by Prof. Vineet Gandhi. During my Bachelor's thesis, I primarily worked on compulational cinematograpy.

Email  /  Google Scholar  /  Github

profile photo
Research

I'm primarily interested in computer vision, machine learning, image processing and computer graphics.

Papers (* equal contribution)
Gazed Gazed–gaze-guided cinematic editing of wide-angle monocular video recordings
K L Bhanu Moorthy, Moneish Kumar, Ramanathan Subramanian, Vineet Gandhi
CHI , 2020
paper / demo
watch_to_edit Watch to edit: Video retargeting using gaze
Moneish Kumar*, Kranthi Kumar Rachavarapu*, Vineet Gandhi, Ramanathan Subramanian
Eurographics , 2018
paper /  demo
Zooming Zooming On All Actors: Automatic Focus+Context Split Screen Video Generation
Moneish Kumar, Vineet Gandhi, Rémi Ronfard, Michael Gleicher
Eurographics , 2017
paper /  demo
Selected Projects
S2NeRF S2NeRF: Semantically Stylized Neural Radiance Fields
Moneish Kumar, Dishani Lahiri, Neeraj Panse, Rupanjali Kukal
Learning for 3D vision , Course Project
Project Website
S2NeRF Coded aperture to obtain depth and focus image
Moneish Kumar
Compulational Photography, Course Project

Source taken from here