An Adversarial Generative Network Designed for High-Resolution Monocular Depth Estimation from 2D HiRISE Images of Mars

In computer vision, stereoscopy allows the three-dimensional reconstruction of a scene using two 2D images taken from two slightly different points of view, to extract spatial information on the depth of the scene in the form of a map of disparities. In stereophotogrammetry, the disparity map is essential in extracting the digital terrain model (DTM) and thus obtaining a 3D spatial mapping, which is necessary for a better analysis of planetary surfaces. However, the entire reconstruction process performed with the stereo-matching algorithm can be time consuming and can generate many artifacts. Coupled with the lack of adequate stereo coverage, it can pose a significant obstacle to 3D planetary mapping. Recently, many deep learning architectures have been proposed for monocular depth estimation, which aspires to predict the third dimension given a single 2D image, with considerable advantages thanks to the simplification of the reconstruction problem, leading to a significant increase in interest in deep models for the generation of super-resolution images and DTM estimation. In this paper, we combine these last two concepts into a single end-to-end model and introduce a new generative adversarial network solution that estimates the DTM at 4× resolution from a single monocular image, called SRDiNet (super-resolution depth image network). Furthermore, we introduce a sub-network able to apply a refinement using interpolated input images to better enhance the fine details of the final product, and we demonstrate the effectiveness of its benefits through three different versions of the proposal: SRDiNet with GAN approach, SRDiNet without adversarial network, and SRDiNet without the refinement learned network plus GAN approach. The results of Oxia Planum (the landing site of the European Space Agency’s Rosalind Franklin ExoMars rover 2023) are reported, applying the best model along all Oxia Planum tiles and releasing a 3D product enhanced by 4×.

PDF Abstract

Datasets


Introduced in the Paper:

Mars DTM Estimation

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Depth Estimation Mars DTM Estimation GLPDepth Delta < 1.25 0.4324 # 1
Delta < 1.25^2 0.6667 # 2
Delta < 1.25^3 0.7949 # 2
Average PSNR 29.2636 # 1
mean absolute error 10.2905 # 2
RMSE 18.3042 # 2
Depth Estimation Mars DTM Estimation SRDINET (Model A) Delta < 1.25 0.3967 # 2
Delta < 1.25^2 0.6731 # 1
Delta < 1.25^3 0.8208 # 1
Average PSNR 15.069 # 2
mean absolute error 0.1558 # 1
RMSE 0.1859 # 1

Methods


No methods listed for this paper. Add relevant methods here