RSINet: Inpainting Remotely Sensed Images Using Triple GAN Framework

Abstract

We tackle the problem of image inpainting in the remote sensing domain. Remote sensing images possess high resolution and geographical variations, that render the conventional inpainting methods less effective. This further entails the requirement of models with high complexity to sufficiently capture the spectral, spatial and textural nuances within an image, emerging from its high spatial variability. To this end, we propose a novel inpainting method that individually focuses on each aspect of an image such as edges, colour and texture using a task specific GAN. Moreover, each individual GAN also incorporates the attention mechanism that explicitly extracts the spectral and spatial features. To ensure consistent gradient flow, the model uses residual learning paradigm, thus simultaneously working with high and low level features. We evaluate our model, alongwith previous state of the art models, on the two well known remote sensing datasets, Open Cities AI and Earth on Canvas, and achieve competitive performance. The code can be referred here: https://github.com/advaitkumar3107/RSINet.

SR-DeblurUGAN: An End-to-End Super-Resolution and Deblurring Model with High Performance

“…Peter, P. proposed a mask optimization network for data optimization in spatial picture-in-picture, with the improvement that a generator and a corresponding optimization network can be jointly trained, with the effect of accurately reflecting the image, achieving a breakthrough in quality and speed. Kumar, A. et al proposed a new patching approach that can use GAN to focus on each aspect of image features, such as color and shape individually, and was validated in two datasets, achieving competitive performance [12]. Jam, J. et al designed a loss model employing two encoders and proposed a recursive residual transition layer that achieved some technical progress in terms of bias and quality for image repair, which was well generalized on a stationary dataset [13].…”