Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Segmentation-Driven Monocular Shape from Polarization based on Physical Model

Jinyu Zhang, Xu Ma, Weili Chen, Gonzalo R. Arce

TL;DR

A segmentation-driven monocular SfP (SMSfP) framework that reformulates global shape recovery into a set of local reconstructions over adaptively segmented convex sub-regions is introduced, showing significant improvements in disambiguation accuracy and geometric fidelity compared with existing physics-based monocular SfP techniques.

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.

Segmentation-Driven Monocular Shape from Polarization based on Physical Model

TL;DR

A segmentation-driven monocular SfP (SMSfP) framework that reformulates global shape recovery into a set of local reconstructions over adaptively segmented convex sub-regions is introduced, showing significant improvements in disambiguation accuracy and geometric fidelity compared with existing physics-based monocular SfP techniques.

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.
Paper Structure (20 sections, 26 equations, 10 figures, 2 tables, 1 algorithm)

This paper contains 20 sections, 26 equations, 10 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Physics-based Methods
  4. Deep-learning-based Methods
  5. Polarization Theory and Problem Formulation
  6. Theoretical Foundation of Polarization
  7. Surface Normal Representation
  8. Diffuse Polarization Model
  9. Proposed Method
  10. Azimuth Angle Constraint
  11. Zenith Angle Constraint
  12. Multi-Scaled Fusion Convexity Prior
  13. Height Estimation and Iterative Parameter Update
  14. Polarization-Driven Region Segmentation
  15. Experiment and Analysis
  16. ...and 5 more sections

Figures (10)

  • Figure 1: The polarized images and the decomposed components: (a) polarized images along the angles of $0^\circ, 45^\circ, 90^\circ$ and $135^\circ$; (b) average intensity image; (c) AOP image; (d) DOP image.
  • Figure 2: The diagram of the proposed SMSfP method.
  • Figure 3: Computational workflow for multi-scale fusion convexity prior constraint.
  • Figure 4: The workflow of PARG segmentation method, where the region growing is applied to the input DOP $\rho$ and AOP $\varphi$, and the post-processing is used to generate the final segmentation.
  • Figure 5: The Polarized imaging testbed consisting of the light source, target, linear polarizer and detector.
  • ...and 5 more figures