PuriLight: A Lightweight Shuffle and Purification Framework for Monocular Depth Estimation

TL;DR

PuriLight is a lightweight, efficient framework for self-supervised monocular depth estimation that combines novel modules to achieve high accuracy with minimal computational resources.

Contribution

The paper introduces a novel three-module architecture that enhances lightweight depth estimation models with structural precision and efficiency.

Findings

Achieves state-of-the-art performance with minimal parameters

Maintains high accuracy while being computationally efficient

Effective feature extraction and purification through novel modules

Abstract

We propose PuriLight, a lightweight and efficient framework for self-supervised monocular depth estimation, to address the dual challenges of computational efficiency and detail preservation. While recent advances in self-supervised depth estimation have reduced reliance on ground truth supervision, existing approaches remain constrained by either bulky architectures compromising practicality or lightweight models sacrificing structural precision. These dual limitations underscore the critical need to develop lightweight yet structurally precise architectures. Our framework addresses these limitations through a three-stage architecture incorporating three novel modules: the Shuffle-Dilation Convolution (SDC) module for local feature extraction, the Rotation-Adaptive Kernel Attention (RAKA) module for hierarchical feature enhancement, and the Deep Frequency Signal Purification (DFSP) module for global feature purification. Through effective collaboration, these modules enable PuriLight to achieve both lightweight and accurate feature extraction and processing. Extensive experiments demonstrate that PuriLight achieves state-of-the-art performance with minimal training parameters while maintaining exceptional computational efficiency. Codes will be available at https://github.com/ishrouder/PuriLight.