MuS-Polar3D: A Benchmark Dataset for Computational Polarimetric 3D Imaging under Multi-Scattering Conditions

TL;DR

MuS-Polar3D addresses the challenge of fair benchmarking for polarization-based underwater 3D imaging under diverse scattering by introducing a large, multi-view dataset with controlled turbidity and high-precision ground truth. It adopts a two-stage pipeline that first descatters polarization images and then performs 3D reconstruction, enabling consistent comparisons with SDF-based and SfM/MVS approaches. The dataset comprises 42 objects, seven scattering levels, up to five viewpoints, and includes normal maps and masks, supporting normal estimation, descattering, segmentation, and 3D reconstruction, with best reported mean angular error of $15.49^{\circ}$. Overall, MuS-Polar3D provides a unified, extensible platform for evaluating polarization cues and multi-view geometry in challenging underwater environments, with strong potential to advance practical 3D vision in turbid waters.

Abstract

Polarization-based underwater 3D imaging exploits polarization cues to suppress background scattering, exhibiting distinct advantages in turbid water. Although data-driven polarization-based underwater 3D reconstruction methods show great potential, existing public datasets lack sufficient diversity in scattering and observation conditions, hindering fair comparisons among different approaches, including single-view and multi-view polarization imaging methods. To address this limitation, we construct MuS-Polar3D, a benchmark dataset comprising polarization images of 42 objects captured under seven quantitatively controlled scattering conditions and five viewpoints, together with high-precision 3D models (+/- 0.05 mm accuracy), normal maps, and foreground masks. The dataset supports multiple vision tasks, including normal estimation, object segmentation, descattering, and 3D reconstruction. Inspired by computational imaging, we further decouple underwater 3D reconstruction under scattering into a two-stage pipeline, namely descattering followed by 3D reconstruction, from an imaging-chain perspective. Extensive evaluations using multiple baseline methods under complex scattering conditions demonstrate the effectiveness of the proposed benchmark, achieving a best mean angular error of 15.49 degrees. To the best of our knowledge, MuS-Polar3D is the first publicly available benchmark dataset for quantitative turbidity underwater polarization-based 3D imaging, enabling accurate reconstruction and fair algorithm evaluation under controllable scattering conditions. The dataset and code are publicly available at https://github.com/WangPuyun/MuS-Polar3D.

Figures (16)

• Figure 1: Overview of MuS-Polar3D. The MuS-Polar3D dataset comprises 42 distinct objects and over 800 well-processed samples. These include both ceramic and resin objects, as well as high-texture and low-texture targets, ensuring substantial diversity across the dataset.
• Figure 2: Pipeline of the MuS-Polar3D dataset construction.
• Figure 3: Schematic diagram of the experimental setup for simulating different scattering intensities and the underwater passive polarization imaging model.
• Figure 4: Schematic illustration of the multi-view imaging.
• Figure 5: Workflow of the normal map rendering based on 3D scanning and geometric registration.