New papers posted to arXiv on memory-efficient deep network training, and on separating illuminants in a single image.
New papers posted to arXiv on internal recurrence-based image modeling, and learning privacy-preserving image encodings.
research
Generating and Exploiting Probabilistic Monocular Depth Estimates
arXiv 2019
Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti
Learning to Separate Multiple Illuminants in a Single Image
CVPR 2019
Zhuo Hui, Ayan Chakrabarti, Kalyan Sunkavalli, Aswin C. Sankaranarayanan
NeuADC: Neural Network-Inspired RRAM-Based Synthesizable Analog-to-Digital Conversion with Reconfigurable Quantization Support
DATE 2019
Weidong Cao, Xin He, Ayan Chakrabarti, Xuan Zhang
Learning Privacy Preserving Encodings through Adversarial Training
WACV 2019
Francesco Pittaluga, Sanjeev J. Koppal, Ayan Chakrabarti
Examining the Impact of Blur on Recognition by Convolutional Networks
arXiv 2017
Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich
Learning Object Color Models from Multi-view Constraints
CVPR 2011
Trevor Owens, Kate Saenko, Ayan Chakrabarti, Ying Xiong, Todd Zickler, Trevor Darrell
Color Constancy Beyond Bags of Pixels
CVPR 2008
Ayan Chakrabarti, Keigo Hirakawa, 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
