PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments

TL;DR

PromptMono introduces a self-supervised monocular depth estimation framework using visual prompts and a novel attention module to improve performance across diverse challenging environments.

Contribution

It proposes a unified model with visual prompt learning and a gated cross prompting attention module for better depth estimation in varied conditions.

Findings

Outperforms existing methods on Oxford Robotcar dataset

Effective in diverse challenging environments

Demonstrates superior accuracy in depth prediction

Abstract

Considerable efforts have been made to improve monocular depth estimation under ideal conditions. However, in challenging environments, monocular depth estimation still faces difficulties. In this paper, we introduce visual prompt learning for predicting depth across different environments within a unified model, and present a self-supervised learning framework called PromptMono. It employs a set of learnable parameters as visual prompts to capture domain-specific knowledge. To integrate prompting information into image representations, a novel gated cross prompting attention (GCPA) module is proposed, which enhances the depth estimation in diverse conditions. We evaluate the proposed PromptMono on the Oxford Robotcar dataset and the nuScenes dataset. Experimental results demonstrate the superior performance of the proposed method.