Segmentation-Driven Monocular Shape from Polarization based on Physical Model

2026-01-08

arXiv.org

AI Summary

This work addresses the challenge of normal estimation bias and geometric distortion in monocular polarization-based 3D reconstruction, which commonly arises from azimuthal angle ambiguity in polarimetric measurements. To mitigate this issue, the authors propose a physics-driven Shape-from-Polarization (SfP) framework that decomposes global shape recovery into adaptive segmentation and reconstruction of locally convex surface regions. By integrating a polarization-guided region-growing strategy with multi-scale convexity priors, the method effectively resolves azimuthal ambiguity while preserving surface continuity. Extensive experiments on both synthetic and real-world datasets demonstrate that the proposed approach significantly outperforms existing physical models, achieving notable improvements in disambiguation accuracy and geometric fidelity.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: State Estimation
• Machine Learning: Feature Construction/Reformulation

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Monocular shape-from-polarization (SfP) leverages the intrinsic relationship between light polarization properties and surface geometry to recover surface normals from single-view polarized images, providing a compact and robust approach for three-dimensional (3D) reconstruction. Despite its potential, existing monocular SfP methods suffer from azimuth angle ambiguity, an inherent limitation of polarization analysis, that severely compromises reconstruction accuracy and stability. This paper introduces a novel segmentation-driven monocular SfP (SMSfP) framework that reformulates global shape recovery into a set of local reconstructions over adaptively segmented convex sub-regions. Specifically, a polarization-aided adaptive region growing (PARG) segmentation strategy is proposed to decompose the global convexity assumption into locally convex regions, effectively suppressing azimuth ambiguities and preserving surface continuity. Furthermore, a multi-scale fusion convexity prior (MFCP) constraint is developed to ensure local surface consistency and enhance the recovery of fine textural and structural details. Extensive experiments on both synthetic and real-world datasets validate the proposed approach, showing significant improvements in disambiguation accuracy and geometric fidelity compared with existing physics-based monocular SfP techniques.

Problem

• monocular shape-from-polarization
• azimuth angle ambiguity
• 3D reconstruction
• surface normals
• polarization

Innovation

• Shape-from-Polarization
• azimuth ambiguity
• adaptive segmentation
• convexity prior
• monocular 3D reconstruction