Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Ayan Chakrabarti

Understanding Robustness of Transformers for Image Classification


Mar 26, 2021
Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit


  Access Paper or Ask Questions

Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments


Dec 09, 2020
Zhihao Xia, Michaël Gharbi, Federico Perazzi, Kalyan Sunkavalli, Ayan Chakrabarti

* Project page at https://www.cse.wustl.edu/~zhihao.xia/deepfnf/ 

  Access Paper or Ask Questions

Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints


Nov 05, 2020
Ayan Chakrabarti, Roch Guérin, Chenyang Lu, Jiangnan Liu

* Code available at https://github.com/ayanc/edgeml.mdp 

  Access Paper or Ask Questions

Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositing


Oct 17, 2020
Jinghan Yang, Adith Boloor, Ayan Chakrabarti, Xuan Zhang, Yevgeniy Vorobeychik


  Access Paper or Ask Questions

A MEMS-based Foveating LIDAR to enable Real-time Adaptive Depth Sensing


Mar 21, 2020
Francesco Pittaluga, Zaid Tasneem, Justin Folden, Brevin Tilmon, Ayan Chakrabarti, Sanjeev J. Koppal

* 17 pages, 6 figures, project site: https://www.fpittaluga.com/adaptivelidar 

  Access Paper or Ask Questions

Basis Prediction Networks for Effective Burst Denoising with Large Kernels


Dec 09, 2019
Zhihao Xia, Federico Perazzi, Michaël Gharbi, Kalyan Sunkavalli, Ayan Chakrabarti


  Access Paper or Ask Questions

Protecting Geolocation Privacy of Photo Collections


Dec 04, 2019
Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik

* AAAI 20 

  Access Paper or Ask Questions

Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices


Nov 28, 2019
Weidong Cao, Liu Ke, Ayan Chakrabarti, Xuan Zhang

* 7 pages, ICCAD 2019 

  Access Paper or Ask Questions

Training Image Estimators without Image Ground-Truth


Jun 13, 2019
Zhihao Xia, Ayan Chakrabarti

* Project page at https://projects.ayanc.org/unsupimg/ 

  Access Paper or Ask Questions

Generating and Exploiting Probabilistic Monocular Depth Estimates


Jun 13, 2019
Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti

* Project page at https://projects.ayanc.org/prdepth/ 

  Access Paper or Ask Questions

Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures


Mar 08, 2019
Kyle Yee, Ayan Chakrabarti

* Project site at https://projects.ayanc.org/fdscs/ 

  Access Paper or Ask Questions

Backprop with Approximate Activations for Memory-efficient Network Training


Jan 23, 2019
Ayan Chakrabarti, Benjamin Moseley

* Project page at http://projects.ayanc.org/blpa/ 

  Access Paper or Ask Questions

Learning to Separate Multiple Illuminants in a Single Image


Nov 29, 2018
Zhuo Hui, Ayan Chakrabarti, Kalyan Sunkavalli, Aswin C. Sankaranarayanan


  Access Paper or Ask Questions

Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning


Sep 14, 2018
Charles Schaff, David Yunis, Ayan Chakrabarti, Matthew R. Walter


  Access Paper or Ask Questions

Stabilizing GAN Training with Multiple Random Projections


Jun 23, 2018
Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti


  Access Paper or Ask Questions

Learning Privacy Preserving Encodings through Adversarial Training


Jun 13, 2018
Francesco Pittaluga, Sanjeev J. Koppal, Ayan Chakrabarti


  Access Paper or Ask Questions

Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising


Jun 13, 2018
Zhihao Xia, Ayan Chakrabarti


  Access Paper or Ask Questions

Jointly Optimizing Placement and Inference for Beacon-based Localization


Sep 20, 2017
Charles Schaff, David Yunis, Ayan Chakrabarti, Matthew R. Walter

* Appeared at 2017 International Conference on Intelligent Robots and Systems (IROS) 

  Access Paper or Ask Questions

Examining the Impact of Blur on Recognition by Convolutional Networks


May 30, 2017
Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich


  Access Paper or Ask Questions

Learning Sensor Multiplexing Design through Back-propagation


Nov 02, 2016
Ayan Chakrabarti

* NIPS 2016. Project page at http://www.ttic.edu/chakrabarti/learncfa 

  Access Paper or Ask Questions

Single-image RGB Photometric Stereo With Spatially-varying Albedo


Sep 14, 2016
Ayan Chakrabarti, Kalyan Sunkavalli

* 3DV 2016. Project page at http://www.ttic.edu/chakrabarti/rgbps/ 

  Access Paper or Ask Questions

Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions


Sep 07, 2016
Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich

* NIPS 2016. Project page at http://www.ttic.edu/chakrabarti/mdepth/ 

  Access Paper or Ask Questions

A Neural Approach to Blind Motion Deblurring


Aug 01, 2016
Ayan Chakrabarti

* ECCV 2016. Project page at http://www.ttic.edu/chakrabarti/ndeblur 

  Access Paper or Ask Questions

Color Constancy by Learning to Predict Chromaticity from Luminance


Dec 07, 2015
Ayan Chakrabarti

* Appears in Advances in Neural Information Processing Systems 28 (NIPS 2015) 

  Access Paper or Ask Questions

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


Apr 14, 2015
Ayan Chakrabarti, Ying Xiong, Steven J. Gortler, Todd Zickler

* Accepted to CVPR 2015. Project page: http://www.ttic.edu/chakrabarti/consensus/ 

  Access Paper or Ask Questions

Modeling Radiometric Uncertainty for Vision with Tone-mapped Color Images


Apr 09, 2014
Ayan Chakrabarti, Ying Xiong, Baochen Sun, Trevor Darrell, Daniel Scharstein, Todd Zickler, Kate Saenko

* IEEE Trans. PAMI 36 (2014) 2185-2198 

  Access Paper or Ask Questions

From Shading to Local Shape


Apr 07, 2014
Ying Xiong, Ayan Chakrabarti, Ronen Basri, Steven J. Gortler, David W. Jacobs, Todd Zickler

* IEEE Trans. PAMI 37 (2015) 67-79 

  Access Paper or Ask Questions

Image Restoration with Signal-dependent Camera Noise


Apr 13, 2012
Ayan Chakrabarti, Todd Zickler

* 6 pages, 3 figures, 2 tables 

  Access Paper or Ask Questions