PROJECT TITLE :
Confidence Measure Guided Single Image De-Raining
ABSTRACT:
Single-image de-raining is a difficult subject since rain streaks fluctuate in size, direction, and density in wet photos. Different sections of the image are affected by the diverse characteristics of rain streaks because of this. Attempts have been made in the past to eliminate rain streaks from a single photograph by leveraging certain prior information. These methods have a key drawback in that they don't take into account the location of rain drops in the image. Image Quality-based single image Deraining using Confidence measure (QuDeC) solves this issue by learning the quality or distortion degree of each patch in the rainy image, and then processing this information to learn the rain content at different scales. The network weights are learned based on a confidence measure for both the quality assessment at each site and the residual rain streak information. In addition (residual map). This method outperforms current state-of-the-art methods by a wide margin, as evidenced by several tests on both synthetic and real datasets
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here
