2 papers
cs.CV2025
Dark Channel-Assisted Depth-from-Defocus from a Single Image
Moushumi Medhi, Rajiv Ranjan Sahay
We estimate scene depth from a single defocus-blurred image using the dark channel as a complementary cue, leveraging its ability to capture local statistics and scene structure. T…
cs.CV2024
Deep Generative Adversarial Network for Occlusion Removal from a Single Image
Sankaraganesh Jonna, Moushumi Medhi, Rajiv Ranjan Sahay
Nowadays, the enhanced capabilities of in-expensive imaging devices have led to a tremendous increase in the acquisition and sharing of multimedia content over the Internet. Despit…