☆ 3.8 Proceedings Paper

Perspective Phase Angle Model for Polarimetric 3D Reconstruction

COMPUTER VISION - ECCV 2022, PT II (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Proceedings Paper Computer Science, Artificial Intelligence

Shape from Polarization for Complex Scenes in the Wild

Chenyang Lei et al.

Summary: We propose a new data-driven approach with physics-based priors for scene-level normal estimation from a single polarization image. Unlike existing shape from polarization (SfP) methods that mainly focus on estimating normal of a single object, we emphasize on estimating normals in complex scenes. By creating a real-world scene-level SfP dataset, we tackle the problem of lack of real data in complex scenes. Our learning framework with multi-head self-attention module and viewing encoding can handle increasing polarization ambiguities caused by complex materials and non-orthographic projection.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Uncalibrated, Two Source Photo-Polarimetric Stereo

Silvia Tozza et al.

Summary: In this paper, we present a method for estimating shape from polarisation and shading information under unknown illumination conditions. We propose alternative photo-polarimetric constraints and demonstrate how to express them using a unified system of partial differential equations, which allows for linear least squares solutions. We also introduce new methods for estimating polarisation images, albedo, and refractive index, and evaluate their performance on both synthetic and real-world data, showing improvements over existing state-of-the-art methods.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Robotics

Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior

Moein Shakeri et al.

Summary: This study focuses on the application of polarization imaging in dense map reconstruction, utilizing relative depth information as a prior to improve the accuracy and density of dense reconstruction, especially in regions with poor texture.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

DEEP SNAPSHOT HDR RECONSTRUCTION BASED ON THE POLARIZATION CAMERA

Juiwen Ting et al.

Summary: The paper explores the use of on-chip micro-polarizer technology in high-dynamic-range imaging, treating multiple images captured by the polarization camera as a set captured under different exposure times. A deep snapshot HDR reconstruction framework is proposed to recover an HDR image using the polarization images, demonstrating favorable performance against state-of-the-art HDR reconstruction algorithms.

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Polarimetric Normal Stereo

Yoshiki Fukao et al.

Summary: This method introduces a novel approach to recovering per-pixel surface normals using polarization cameras, integrating polarimetric observations for direct recovery of surface normals. By modeling polarimetric light reflection of mesoscopic surface roughness, it offers effective 3D sensing capability for complex, non-Lambertian surfaces.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Robotics

HDR Reconstruction Based on the Polarization Camera

Xuesong Wu et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Scale Geometric Consistency Guided Multi-View Stereo

Qingshan Xu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Linear Differential Constraints for Photo-polarimetric Height Estimation

Silvia Tozza et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Shape-from-polarisation: a nonlinear least squares approach

Ye Yu et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Polarimetric Multi-View Stereo

Zhaopeng Cui et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Linear Depth Estimation from an Uncalibrated, Monocular Polarisation Image

William A. P. Smith et al.

COMPUTER VISION - ECCV 2016, PT VIII (2016)

添加到收藏夹

Article Optics

The polarization properties of a tilted polarizer

Jan Korger et al.

OPTICS EXPRESS (2013)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Multi-view Photometric Stereo with Spatially Varying Isotropic Materials

Zhenglong Zhou et al.

2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Shape estimation using polarization and shading from two views

Gary A. Atkinson et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2007)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Recovery of surface orientation from diffuse polarization

Gary A. Atkinson et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.