Neural 3D Reconstruction of Planetary Surfaces from Descent-Phase Wide-Angle Imagery

TL;DR

This paper explores neural reconstruction methods for planetary surface modeling from descent-phase wide-angle images, addressing challenges like distortion and limited parallax.

Contribution

It introduces a novel neural height field approach tailored for planetary terrain reconstruction, outperforming traditional methods in coverage and accuracy.

Findings

Neural methods provide a competitive alternative to multi-view stereo.

The proposed approach achieves higher spatial coverage on lunar and Mars terrains.

Experiments demonstrate effective reconstruction despite imaging challenges.

Abstract

Digital elevation modeling of planetary surfaces is essential for studying past and ongoing geological processes. Wide-angle imagery acquired during spacecraft descent promises to offer a low-cost option for high-resolution terrain reconstruction. However, accurate 3D reconstruction from such imagery is challenging due to strong radial distortion and limited parallax from vertically descending, predominantly nadir-facing cameras. Conventional multi-view stereo exhibits limited depth range and reduced fidelity under these conditions and also lacks domain-specific priors. We present the first study of modern neural reconstruction methods for planetary descent imaging. We also develop a novel approach that incorporates an explicit neural height field representation, which provides a strong prior since planetary surfaces are generally continuous, smooth, solid, and free from floating objects. This study demonstrates that neural approaches offer a strong and competitive alternative to traditional multi-view stereo (MVS) methods. Experiments on simulated descent sequences over high-fidelity lunar and Mars terrains demonstrate that the proposed approach achieves increased spatial coverage while maintaining satisfactory estimation accuracy.