M3Depth: Wavelet-Enhanced Depth Estimation on Mars via Mutual Boosting of Dual-Modal Data

TL;DR

M3Depth is a novel depth estimation model for Mars rovers that leverages wavelet transforms and mutual boosting of depth and surface normal maps to improve accuracy in unstructured terrains.

Contribution

The paper introduces a wavelet-based convolutional approach and a mutual boosting mechanism for depth and normal maps, tailored for Martian terrain challenges.

Findings

Achieves 16% improvement in depth accuracy over state-of-the-art methods.

Effectively captures low-frequency features of Martian terrain.

Demonstrates strong applicability in real Martian scenarios.

Abstract

Depth estimation plays a great potential role in obstacle avoidance and navigation for further Mars exploration missions. Compared to traditional stereo matching, learning-based stereo depth estimation provides a data-driven approach to infer dense and precise depth maps from stereo image pairs. However, these methods always suffer performance degradation in environments with sparse textures and lacking geometric constraints, such as the unstructured terrain of Mars. To address these challenges, we propose M3Depth, a depth estimation model tailored for Mars rovers. Considering the sparse and smooth texture of Martian terrain, which is primarily composed of low-frequency features, our model incorporates a convolutional kernel based on wavelet transform that effectively captures low-frequency response and expands the receptive field. Additionally, we introduce a consistency loss that explicitly models the complementary relationship between depth map and surface normal map, utilizing the surface normal as a geometric constraint to enhance the accuracy of depth estimation. Besides, a pixel-wise refinement module with mutual boosting mechanism is designed to iteratively refine both depth and surface normal predictions. Experimental results on synthetic Mars datasets with depth annotations show that M3Depth achieves a 16% improvement in depth estimation accuracy compared to other state-of-the-art methods in depth estimation. Furthermore, the model demonstrates strong applicability in real-world Martian scenarios, offering a promising solution for future Mars exploration missions.