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

2026-04-14

AI Summary

This work addresses the challenges of stereo image restoration in complex degradation environments—such as underwater, hazy, and low-light conditions—where diverse physical degradations and severe information loss hinder performance. Existing datasets are often limited to a single degradation type or lack stereo consistency. To bridge this gap, we introduce M3D-Stereo, a high-resolution dataset comprising 7,904 stereo image pairs captured across multiple media, encompassing four degradation types at six progressive severity levels, all accompanied by pixel-aligned clean ground truth. M3D-Stereo is the first to enable realistic modeling of multi-medium, multi-degradation, and multi-level distortions while preserving stereo consistency, supporting both single-level and mixed-level restoration tasks. Leveraging controlled laboratory acquisition and high-precision alignment, the dataset significantly enhances the fidelity and reliability of evaluating image restoration and stereo matching algorithms in complex scenarios. The dataset is publicly released under the LGPLv3 license.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

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.

Problem

• stereo image restoration
• multiple degradation
• adverse conditions
• realistic benchmark
• image degradations

Innovation

• stereo image restoration
• multiple degradation
• real-world dataset
• controlled degradation levels
• pixel-wise ground truth