Guha Balakrishnan



32-D466 Vassar St.
Cambridge, MA

About Me

Hello! I am a postdoctoral researcher in Bill Freeman’s group at MIT working at the intersection of computer vision, machine learning, and computer graphics.

I am interested in using learning-based image synthesis methods to reason about causal processes or low-dimensional structure underlying our data. Some topics I am interested in include stochastic image/video prediction, ill-posed reconstruction, bias auditing of AI systems, and medical applications. Please take a look below at my projects.

I completed my Master’s (2013) and Ph.D. (2018) degrees in the EECS department at MIT, advised by John Guttag and Frédo Durand. My Ph.D. dissertation was titled Analyzing and Synthesizing Deformations in Image Datasets. My Master's dissertation focused on vitals signs measurement from video recordings.

I completed my B.S.E. degrees in Computer Science and Computer Engineering at the University of Michigan, Ann Arbor in 2011.

Some Projects By Category

Image/Video Synthesis

Learning-based approach that synthesizes plausible painting timelapses given only a finished painting.

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
A. Zhao, G. Balakrishnan, K.M. Lewis, F. Durand, J. Guttag, A. V. Dalca
In Submission
Learning-based approach that synthesizes plausible 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,
W.T. Freeman.
ICCV 2019

mit news, engadget, petapixel, science daily, techspot

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
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

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

mit news, nvidia, innovatorsmag, extremetech, semiengineering, physicsworld, electronics360, radiologybusiness, futurelab3d, techexplorist, healthimaging, acceleratingbiz, bionengineeringtoday
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
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
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, best paper runner-up)
paper, code

Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces.
A.V. Dalca, G. Balakrishnan, J. Guttag, M.R. Sabuncu.
Medical Image Analysis (MedIA), 2019

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

mit news,, newscientist, cnet, fox news, sciencenews, kurzweilai
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.
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.