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

ArXi:2604.12917v1 Announce Type: new 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