Ayan Chakrabarti
Assistant Professor

Computer Science & Engineering
School of Engineering & Applied Science
Washington University in St. Louis

E-mail: ayan [at] wustl [dot] edu
Office: Jolley Hall 205

I work on problems in computer vision, computational photography, and machine learning—dealing with the design of accurate and efficient algorithms for visual inference, and of new kinds of high-capability sensors and cameras. I seek solutions to these problems by considering the physics of image formation, and the statistical structure of natural images and scenes.

[Google Scholar]   [GitHub]   [arXiv]   [CV]

I am looking to recruit talented PhD students interested in computer vision. Please apply directly to the CSE PhD program at WashU.

news /  teaching /  research /  students /  code /  data 


Sep 2017Joined WashU as Assistant Professor in CSE.
Jun 2017Work on learning beacon placement accepted to appear at IROS 2017.
May 2017New paper on stable GAN training posted to arXiv.
May 2017Will be serving as area chair for 3DV 2017 and CVPR 2018.


CSE 559A Computer Vision: Fall 2017


Stabilizing GAN Training with Multiple Random Projections
arXiv 2017

Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti
Paper: arXiv    URL: Project website

Jointly Optimizing Placement and Inference for Beacon-based Localization
IROS 2017

Charles Schaff, David Yunis, Ayan Chakrabarti, Matthew R. Walter
Paper: arXiv    URL: Project website

Learning Sensor Multiplexing Design through Back-propagation
NIPS 2016

Ayan Chakrabarti
Paper: arXiv    URL: Project website

Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
NIPS 2016

Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich
Paper: arXiv    URL: Project website

Single-image RGB Photometric Stereo With Spatially-varying Albedo
3DV 2016 Oral

Ayan Chakrabarti, Kalyan Sunkavalli
Paper: arXiv    URL: Project website

A Neural Approach to Blind Motion Deblurring
ECCV 2016

Ayan Chakrabarti
Paper: arXiv    URL: Project website

Color Constancy by Learning to Predict Chromaticity from Luminance
NIPS 2015 Spotlight

Ayan Chakrabarti
Paper: arXiv (w/ supp. section) / NIPS    URL: Project website

Low-level Vision by Consensus in a Spatial Hierarchy of Regions
CVPR 2015

Ayan Chakrabarti, Ying Xiong, Steven J. Gortler, Todd Zickler
Paper: CV-F / arXiv    URL: Project website

From Shading to Local Shape
PAMI, Jan 2015

Ying Xiong, Ayan Chakrabarti, Ronen Basri, Steven J. Gortler, David W. Jacobs, Todd Zickler
Paper: IEEE Xplore / arXiv    URL: Project website

Modeling Radiometric Uncertainty for Vision with Tone-mapped Color Images
PAMI, Nov 2014

Ayan Chakrabarti, Ying Xiong, Baochen Sun, Trevor Darrell, Daniel Scharstein, Todd Zickler, Kate Saenko
Paper: IEEE Xplore / arXiv    URL: Project website

Rethinking Color Cameras
ICCP 2014

Ayan Chakrabarti, William T. Freeman, Todd Zickler
Paper: IEEE Xplore    URL: Project website

Depth and Deblurring from a Spectrally-varying Depth-of-Field
ECCV 2012

Ayan Chakrabarti, Todd Zickler
Paper: PDF    URL: Project website, Spotlight Video

Color Constancy with Spatio-Spectral Statistics
PAMI, Aug 2012

Ayan Chakrabarti, Keigo Hirakawa, Todd Zickler
Paper: IEEE Xplore    URL: Project website

Statistics of Real-World Hyperspectral Images
CVPR 2011

Ayan Chakrabarti, Todd Zickler
Paper: IEEE Xplore    URL: Project website

Learning Object Color Models from Multi-view Constraints
CVPR 2011

Trevor Owens, Kate Saenko, Ayan Chakrabarti, Ying Xiong, Todd Zickler, Trevor Darrell
Paper: IEEE Xplore

Analyzing Spatially-varying Blur
CVPR 2010

Ayan Chakrabarti, Todd Zickler, William T. Freeman
Paper: IEEE Xplore    URL: Project website

An Empirical Camera Model for Internet Color Vision
BMVC 2009

Ayan Chakrabarti, Daniel Scharstein, Todd Zickler
Paper: PDF    URL: Project website

Color Constancy Beyond Bags of Pixels
CVPR 2008

Ayan Chakrabarti, Keigo Hirakawa, Todd Zickler
Paper: IEEE Xplore

Effective Separation of Sparse and Non-sparse Image Features for Denoising

Ayan Chakrabarti, Keigo Hirakawa
Paper: IEEE Xplore

Super-Resolution of Face Images Using Kernel PCA-Based Prior
IEEE Transactions on Multimedia, June 2007

Ayan Chakrabarti, A.N. Rajagopalan, Rama Chellappa
Paper: IEEE Xplore

Visual Inference with Statistical Models for Color and Texture
Ph.D. Dissertation, School of Engineering and Applied Sciences, Harvard University, 2011

Ayan Chakrabarti

Acknowledgments: My work is / has been supported generously by the National Science Foundation (IIS:1618021), and by gifts from Adobe and NVIDIA.


reference implementations


Shape From Shading Evaluation Set

Images of uniform-albedo Lambertian objects under directional lighting, with ground truth normals computed using multi-image photometric stereo.

Download Page

Camera Color Calibration Datasets

RAW-JPEG pairs of calibration targets captured with different consumer cameras. Useful for the analysis and calibration of camera color processing pipelines.

PAMI 2014 version   /   BMVC 2009 version (more cameras, but fewer sampled colors per camera)

Real-world Hyperspectral Image Database

Database of hyperspectral images of natural scenes, with 31 narrow-band spectral measurements in the visible range at each pixel.

Download Page

Motion Blur Database

Database of still images with motion-blurred moving subjects, to qualitatively evaluate algorithms that seek to estimate spatially-varying blur.

Download Page