I am a Research Scientist at Google research in New York. I am interested in problems in machine learning, computer vision, and computational photography.
I received my PhD advised by Todd Zickler at Harvard University, and did my undergraduate studies at IIT Madras. Before joining Google, I was an assistant professor of computer science at WashU, a research assistant professor at the Toyota Technological Institute at Chicago, and a post-doctoral fellow at Harvard.
Google Scholar / GitHub / CV / E-mail
Research
Leveraging Redundancy in Attention with Reuse Transformers
arXiv 2021
Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit, Michal Lukasik, Himanshu Jain, Frederick Liu, Yin-Wen Chang, Sanjiv Kumar
Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
arXiv 2021
Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain, Sanjiv Kumar, Michal Lukasik, Andreas Veit
Understanding Robustness of Transformers for Image Classification
ICCV 2021
Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit
Can Optical Trojans Assist Adversarial Perturbations?
AROW (ICCV) 2021
Adith Boloor, Tong Wu, Patrick Naughton, Ayan Chakrabarti, Xuan Zhang, Yevgeniy Vorobeychik
Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
CVPR 2021
Zhihao Xia, Michaël Gharbi, Federico Perazzi, Kalyan Sunkavalli, Ayan Chakrabarti
Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints
SEC 2021
Ayan Chakrabarti, Roch Guérin, Chenyang Lu, Jiangnan Liu
Generating and Exploiting Probabilistic Monocular Depth Estimates
CVPR 2020 (oral)
Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti
Basis Prediction Networks for Effective Burst Denoising with Large Kernels
CVPR 2020
Zhihao Xia, Federico Perazzi, Michaël Gharbi, Kalyan Sunkavalli, Ayan Chakrabarti
Protecting Geolocation Privacy of Photo Collections
AAAI 2020
Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik
Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
WACV 2020
Zhihao Xia, Ayan Chakrabarti
Training Image Estimators without Image Ground-Truth
NeurIPS 2019 (spotlight)
Zhihao Xia, Ayan Chakrabarti
Backprop with Approximate Activations for Memory-efficient Network Training
NeurIPS 2019
Ayan Chakrabarti, Benjamin Moseley
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
ICCAD 2019 + TCAD
Weidong Cao, Liu Ke, Ayan Chakrabarti, Xuan Zhang
Learning to Separate Multiple Illuminants in a Single Image
CVPR 2019
Zhuo Hui, Ayan Chakrabarti, Kalyan Sunkavalli, Aswin C. Sankaranarayanan
Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
ICRA 2019
Charles Schaff, David Yunis, Ayan Chakrabarti, Matthew R. Walter
NeuADC: Neural Network-Inspired RRAM-Based Synthesizable Analog-to-Digital Conversion with Reconfigurable Quantization Support
DATE 2019 + TCAD
Weidong Cao, Xin He, Ayan Chakrabarti, Xuan Zhang
Learning Privacy Preserving Encodings through Adversarial Training
WACV 2019
Francesco Pittaluga, Sanjeev J. Koppal, Ayan Chakrabarti
Stabilizing GAN Training with Multiple Random Projections
arXiv 2018
Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti
Jointly Optimizing Placement and Inference for Beacon-based Localization
IROS 2017
Charles Schaff, David Yunis, Ayan Chakrabarti, Matthew R. Walter
Examining the Impact of Blur on Recognition by Convolutional Networks
arXiv 2017
Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
NeurIPS 2016
Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich
Single-image RGB Photometric Stereo With Spatially-varying Albedo
3DV 2016 (oral)
Ayan Chakrabarti, Kalyan Sunkavalli
Low-level Vision by Consensus in a Spatial Hierarchy of Regions
CVPR 2015
Ayan Chakrabarti, Ying Xiong, Steven J. Gortler, Todd Zickler
From Shading to Local Shape
PAMI 2015
Ying Xiong, Ayan Chakrabarti, Ronen Basri, Steven J. Gortler, David W. Jacobs, Todd Zickler
Modeling Radiometric Uncertainty for Vision with Tone-mapped Color Images
PAMI 2014
Ayan Chakrabarti, Ying Xiong, Baochen Sun, Trevor Darrell, Daniel Scharstein, Todd Zickler, Kate Saenko
Depth and Deblurring from a Spectrally-varying Depth-of-Field
ECCV 2012
Ayan Chakrabarti, Todd Zickler
Color Constancy with Spatio-Spectral Statistics
PAMI 2012
Ayan Chakrabarti, Keigo Hirakawa, Todd Zickler
Learning Object Color Models from Multi-view Constraints
CVPR 2011
Trevor Owens, Kate Saenko, Ayan Chakrabarti, Ying Xiong, Todd Zickler, Trevor Darrell
An Empirical Camera Model for Internet Color Vision
BMVC 2009
Ayan Chakrabarti, Daniel Scharstein, Todd Zickler
Effective Separation of Sparse and Non-sparse Image Features for Denoising
ICASSP 2008
Ayan Chakrabarti, Keigo Hirakawa
Super-Resolution of Face Images Using Kernel PCA-Based Prior
IEEE Transactions on Multimedia 2007
Ayan Chakrabarti, A.N. Rajagopalan, Rama Chellappa
Visual Inference with Statistical Models for Color and Texture
Ph.D. Dissertation, Harvard University, 2011
Ayan Chakrabarti
Teaching
Service
This site uses Google Analytics for visitor stats, which collects and processes visitor data and sets/reads cookies as described here.
Get website source. Design inspired by Jon's site.