M3D-Stereo: A Multiple-Medium and Multiple-Degradation Dataset for Stereo Image Restoration
For researchers in image restoration and stereo matching, this dataset fills the gap of a controlled, multi-degradation stereo benchmark, though it is an incremental contribution as a new dataset rather than a novel method.
M3D-Stereo introduces a stereo dataset with 7904 high-resolution image pairs across four degradation scenarios (underwater, haze/fog, low-light) with six severity levels, enabling fine-grained evaluation of image restoration methods. The dataset provides aligned stereo pairs with clear ground truths and supports single- and mixed-level degradation tasks.
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.