Hello! I am Bindita Chaudhuri. I am a 5th (final) year Ph.D. student in the Paul G. Allen School of Computer Science and Engineering at University of Washington. I work in the Graphics and Imaging Laboratory under the guidance of Prof. Linda Shapiro. I also collaborate with Alex Colburn, Barbara Mones and Gary Faigin.

My research interests are in the fields of computer vision, machine learning, computer graphics and computational photography. I have worked on developing real-time deep learning frameworks to automatically transfer human facial motion from 2D images to 3D characters for immersive VR/AR/MR storytelling and communication. At present, I am working on photorealistic human avatar generation and 2D-to-3D body motion retargeting.

Previously, I completed my Masters in Electrical Engineering from Indian Institute of Technology Bombay under the guidance of Prof. Subhasis Chaudhuri in 2016 and received my Bachelors degree in Electronics and Telecommunication Engineering from Jadavpur University under the guidance of Prof. Iti Saha Misra in 2014.

Work Experience
Research Intern (Summer 2020)

Virtual Humans team, Facebook Reality Labs / Oculus Research (Sausalito, CA)

Photorealistic texture synthesis for 3D humans

Research Contractor (Jan 2019 - May 2020)

AI Perception and Mixed Reality Platform team, Microsoft Cloud & AI (Redmond, WA)

Personalized face modeling for high-fidelity 3D reconstruction and improved 3D tracking and retargeting from 2D images.

Research Intern (Summer 2018)

Visual Intelligence group, Microsoft Research (Redmond, WA)

Designed a multi-task deep learning framework to transfer performance of single or multiple human faces captured with a 2D camera to 3D animated characters in real time.

Integrated in Puppets feature of Swiftkey! [Blog post] || [Media report]

Graduate Intern Technical (Summer 2017)

Computational Imaging Lab, Intel Labs (Santa Clara, CA)

Designed convolutional neural networks to perform optical flow prediction and image super-resolution for efficient view synthesis from high-definition multi-camera array images.

US patent granted!

Visiting Researcher (Summer 2015)

Department of Information Engineering and Computer Science, University of Trento (Trento, Italy)

Worked with Prof. Lorenzo Bruzzone and Prof. Begum Demir on novel unsupervised and semi-supervised approaches to content-based retrieval of remote sensing images using an inexact graph matching strategy.

Teaching Assistant (September 2016 - Present)

University of Washington (Seattle, WA)

Courses taught: Computer Vision, Artificial Intelligence, Algorithms, Compilers

Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans


Bindita Chaudhuri, Nikolaos Sarafianos, Linda Shapiro, Tony Tung

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting


Bindita Chaudhuri, Noranart Vesdapunt, Linda Shapiro, Baoyuan Wang

IEEE European Conference on Computer Vision (ECCV), 2020 Spotlight!

Joint Face Detection and Facial Motion Retargeting for Multiple Faces


Bindita Chaudhuri, Noranart Vesdapunt, Baoyuan Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

GestureCalc: An Eyes-Free Calculator for Touch Screens


Bindita Chaudhuri*, Leah Perlmutter*, Justin Petelka, Philip Garrison, James Fogarty, Jacob Wobbrock, Richard Ladner (* equal contribution)

ACM SIGACCESS Conference on Computers & Accessibility (ASSETS), 2019

View Interpolation of Multi-Camera Array Images with Flow Estimation and Image Super Resolution using Deep Learning

Bindita Chaudhuri, Fan Zhang, Oscar Nestares

US Patent 10,547,823, 2020

Learning to Generate 3D Stylized Character Expressions from Humans


Deepali Aneja, Bindita Chaudhuri, Alex Colburn, Gary Faigin, Linda Shapiro and Barbara Mones

IEEE Winter Conference on Applications of Computer Vision (WACV), 2018

People's Choice Award! [Allen School News] [Geekwire article]

Multi-label Remote Sensing Image Retrieval using a Semi-Supervised Graph-Theoretic Method


Bindita Chaudhuri, Begüm Demir, Lorenzo Bruzzone and Subhasis Chaudhuri

IEEE Transactions on Geoscience and Remote Sensing (TGRS), vol. 56, no. 2, pp. 1144-1158, Feb 2018

Region-Based Retrieval of Remote Sensing Images using an Unsupervised Graph-Theoretic Approach


Bindita Chaudhuri, Begüm Demir, Lorenzo Bruzzone and Subhasis Chaudhuri

IEEE Geoscience and Remote Sensing Letters (GRSL), vol. 13, no. 7, pp. 987-991, July 2016

Local Collision Avoidance using Laser Sensors for a Nano-Drone

Bindita Chaudhuri, Chung-Yi Weng, Melanie Anderson
Robotics (UW CSE 571) Project, 2019

Stabilization and Real-time Object Tracking in Videos

Bindita Chaudhuri, Heena Gupta, Sania Qamar
Computer Vision (IITB CS 763) Project, 2015

Contact Me


CSE 482, Paul G. Allen Center
185 Stevens Way, Seattle, WA 98195