RSINet: Inpainting Remotely Sensed Images Using Triple GAN Framework
This addresses the problem of reconstructing missing or damaged areas in remote sensing images for applications like environmental monitoring or urban planning, but appears incremental as it builds on existing GAN and attention techniques.
The paper tackles image inpainting for remote sensing images, which have high resolution and geographical variations that challenge conventional methods, by proposing RSINet using a triple GAN framework with attention mechanisms and residual learning. It achieves competitive performance on two remote sensing datasets, Open Cities AI and Earth on Canvas.
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.