Depth Estimation of Martian Surface using ISRO’s MARS Color Camera Images

Depth estimation from satellite images is a fundamental task when studying the terrain of a cetestiat body. Existing solutions for depth estimation often use datasets that include either images of an indoor scene or images related to (self-driving). This paper presents a Pix2pix type of neural network for computing the depth of the Martian surface using the images captured by IRSRO’s Mars Orbiter. In this paper, we have implemented Pix2Pix (Generator Discriminator) architecture using two different toss functions-LSGAN and Vanilla toss functions and then compared their results to select a better toss function for computing accurate depth maps. We also created our own dataset using images provided by ISRO that contains 343 Training Images and 37 testing images.