M3D-Stereo: A Multiple-Medium and Multiple-Degradation Dataset for Stereo Image Restoration

TL;DR

M3D-Stereo is a comprehensive stereo image dataset with multiple media and degradation levels, designed to advance restoration methods in complex real-world environments.

Contribution

The paper introduces M3D-Stereo, a new large-scale, multi-degradation stereo dataset with aligned ground truths for improved evaluation of restoration techniques.

Findings

Dataset includes 7904 high-resolution stereo pairs across four degradation scenarios.

Provides six levels of degradation severity for detailed performance assessment.

Validates the dataset with single-level and mixed-level degradation restoration tasks.

Abstract

Image restoration under adverse conditions, such as underwater, haze or fog, and low-light environments, remains a highly challenging problem due to complex physical degradations and severe information loss. Existing datasets are predominantly limited to a single degradation type or heavily rely on synthetic data without stereo consistency, inherently restricting their applicability in real-world scenarios. To address this, we introduce M3D-Stereo, a stereo dataset with 7904 high-resolution image pairs for image restoration research acquired in multiple media with multiple controlled degradation levels. It encompasses four degradation scenarios: underwater scatter, haze/fog, underwater low-light, and haze low-light. Each scenario forms a subset, and is divided into six levels of progressive degradation, allowing fine-grained evaluations of restoration methods with increasing severity of degradation. Collected via a laboratory setup, the dataset provides aligned stereo image pairs along with their pixel-wise consistent clear ground truths. Two restoration tasks, single-level and mixed-level degradation, were performed to verify its validity. M3D-Stereo establishes a better controlled and more realistic benchmark to evaluate image restoration and stereo matching methods in complex degradation environments. It is made public under LGPLv3 license.