Face


Email:
balakg@mit.edu

Address:
32-D466 Vassar St.
Cambridge, MA
02139

Guha Balakrishnan

About Me

Hello! I am a postdoctoral associate in Bill Freeman’s group at MIT working on computer vision, machine learning, and graphics research. My main interests are in stochastic image/video prediction, medical image analysis, causality in computer vision, and healthcare applications.

I completed my Master’s (2013) and PhD (2018) degrees in the EECS department at MIT, advised by Professors John Guttag and Frédo Durand. My PhD thesis was titled Analyzing and Synthesizing Deformations in Image Datasets. I explored how modeling deformations is useful for applications such as image warping/synthesis, image registration, and action alignment in videos. My Master's thesis focused on vitals signs measurement from video recordings.

Prior to MIT, I completed my bachelor of science degrees in Computer Science and Computer Engineering at the University of Michigan, Ann Arbor.

Some Projects By Category

Image/Video Synthesis


vdp-teaser
A learning-based approach that synthesizes images/videos from projected, lower-dimensional observations.

Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions in Images and Videos.
G. Balakrishnan, A. V. Dalca, A. Zhao, J. Guttag, F. Durand,
B. Freeman.
ICCV 2019

pose teaser
A modular neural network design that synthesizes high-quality images of human poses in new poses.

Synthesizing Images of Humans in Unseen Poses.
G. Balakrishnan, A. Zhao, A. V. Dalca, F. Durand, J. Guttag.
CVPR, 2018 (oral)
paper, code
csail news
videodiff-teaser
A fast, robust method to compare the spatiotemporal differences between a pair of videos depicting similar motions.

Video diff: highlighting differences between similar actions in videos.
G. Balakrishnan,  F. Durand, J. Guttag.
Siggraph Asia, 2015 (oral)
project page

Medical Image Analysis


voxelmorph
We introduce Voxelmorph, an unsupervised method that registers medical images as accurately as the state-of-the-art, but orders of magnitude more quickly.

An Unsupervised Learning Model for Deformable Medical Image Registration.
G. Balakrishnan, A. Zhao, M. R. Sabuncu, J. Guttag, A. V. Dalca.
CVPR, 2018
paper, code

Press:
mit news, nvidia, innovatorsmag, extremetech, semiengineering, physicsworld, electronics360, radiologybusiness, futurelab3d, techexplorist, healthimaging, acceleratingbiz, bionengineeringtoday
tmi-teaser
Presents a semi-supervised version of VoxelMorph, along with substantial experimental analysis.

VoxelMorph: A Learning Framework for Deformable Medical Image Registration.
G. Balakrishnan, A. Zhao, M.R. Sabuncu, J. Guttag, A. V. Dalca.
IEEE TMI: Transactions in Medical Imaging, 2019
paper
augmentation
A trainable augmentation method that learns independent models of spatial and appearance transforms, and uses them to synthesize new training examples.

Data augmentation using learned transforms for one-shot medical image segmentation.
A. Zhao, G. Balakrishnan, F. Durand, J. Guttag, A. V. Dalca.
CVPR, 2019 (oral)
paper, code
miccai
A probablistic, diffeomorphic version of VoxelMorph with the same accuracy and speed as the original.

Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration.
A. V. Dalca, G. Balakrishnan, J. Guttag, and M. R. Sabuncu.
MICCAI, 2018 (oral)
paper, code
media-gm

Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces.
A.V. Dalca, G. Balakrishnan, J. Guttag, M.R. Sabuncu.
Under Review

Healthcare Projects


pulse teaser
A method that extracts accurate pulse signals from video recordings by measuring subtle head movements.

Detecting Pulse from Head Motions in Video.
G. Balakrishnan,  F. Durand, J. Guttag.
CVPR, 2013.
project page

Press:
mit news, phys.org, newscientist, cnet, fox news, sciencenews, kurzweilai
ataxia
An automated method that uses pose estimation and motion features to predict ratings of neurological movement disorder severity from videos of motor exams.

A Video-Based Method for Objectively Rating Ataxia.
R. Jaroensri, A. Zhao, G. Balakrishnan, D. Lo, J. Schmahmann, J. Guttag, F. Durand.
MLHC, 2017.
paper
eeg
A method that reduces the number of time-series data examples needed to accurately train epileptic seizure detectors.
Scalable personalization of long-term physiological monitoring: Active learning methodologies for epileptic seizure onset detection.
G. Balakrishnan, Z. Syed.
AISTATS, 2012.
paper