Sobhan Kanti Dhara — accepted AI-conference papers

2021

Zero-Shot Single Image Restoration Through Controlled Perturbation of Koschmieder's Model

Aupendu Kar, Sobhan Kanti Dhara, Debashis Sen, Prabir Kumar Biswas

CVPR 2021poster

Real-world image degradation due to light scattering can be described based on the Koschmieder's model. Training deep models to restore such degraded images is challenging as real-world paired data is scarcely available and synthetic paired data may suffer from domain-shift issues. In this paper, a…

Cited by 74 PDF ↗Scholar ↗

2019

Maximally Separated Averages Prediction for High Fidelity Reversible Data Hiding

Dibakar Hazarika, Sobhan Kanti Dhara, Debashis Sen

ICASSP 2019accepted

Recently pixel pairing and pixel sorting/selection have been used in prediction-error expansion based reversible data hiding schemes to generate low entropy prediction-error histograms (PEH) necessary for achieving high fidelity. Such schemes generally use the four-neighbor average rhombus predictor…

Cited by 0 Source ↗Scholar ↗