GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors

• URL: http://arxiv.org/abs/2403.11899v1
• Date: Mon, 18 Mar 2024 15:58:03 GMT
• Title: GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
• Authors: LI Yang, WU Ruizheng, LI Jiyong, CHEN Ying-cong,
• Abstract summary: Learning surfaces from neural radiance field (NeRF) became a rising topic in Multi-View Stereo (MVS) Recent methods demonstrated their ability to reconstruct accurate 3D shapes of Lambertian scenes. However, their results on reflective scenes are unsatisfactory due to the entanglement of specular radiance and complicated geometry.
• Score: 8.8400072344375
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Learning surfaces from neural radiance field (NeRF) became a rising topic in Multi-View Stereo (MVS). Recent Signed Distance Function (SDF)-based methods demonstrated their ability to reconstruct accurate 3D shapes of Lambertian scenes. However, their results on reflective scenes are unsatisfactory due to the entanglement of specular radiance and complicated geometry. To address the challenges, we propose a Gaussian-based representation of normals in SDF fields. Supervised by polarization priors, this representation guides the learning of geometry behind the specular reflection and captures more details than existing methods. Moreover, we propose a reweighting strategy in the optimization process to alleviate the noise issue of polarization priors. To validate the effectiveness of our design, we capture polarimetric information, and ground truth meshes in additional reflective scenes with various geometry. We also evaluated our framework on the PANDORA dataset. Comparisons prove our method outperforms existing neural 3D reconstruction methods in reflective scenes by a large margin.

Related papers

• ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction [50.07671826433922]
  It is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics. We propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal. Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures.
  arXiv  Detail & Related papers  (2024-08-22T17:59:01Z)
• RaNeuS: Ray-adaptive Neural Surface Reconstruction [87.20343320266215]
  We leverage a differentiable radiance field eg NeRF to reconstruct detailed 3D surfaces in addition to producing novel view renderings. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor. Our proposed textitRaNeuS are extensively evaluated on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:54:25Z)
• NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images [62.752710734332894]
  NeRSP is a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. We derive photometric and geometric cues from the polarimetric image formation model and multiview azimuth consistency. We achieve the state-of-the-art surface reconstruction results with only 6 views as input.
  arXiv  Detail & Related papers  (2024-06-11T09:53:18Z)
• UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections [92.38975002642455]
  We propose UniSDF, a general purpose 3D reconstruction method that can reconstruct large complex scenes with reflections. Our method is able to robustly reconstruct complex large-scale scenes with fine details and reflective surfaces.
  arXiv  Detail & Related papers  (2023-12-20T18:59:42Z)
• SpecNeRF: Gaussian Directional Encoding for Specular Reflections [43.110815974867315]
  We propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. It enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients.
  arXiv  Detail & Related papers  (2023-12-20T15:20:25Z)
• RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction [3.1820300989695833]
  This paper introduces a versatile paradigm for integrating multi-view reflectance and normal maps acquired through photometric stereo. Our approach employs a pixel-wise joint re- parameterization of reflectance and normal, considering them as a vector of radiances rendered under simulated, varying illumination. It significantly improves the detailed 3D reconstruction of areas with high curvature or low visibility.
  arXiv  Detail & Related papers  (2023-12-02T19:49:27Z)
• MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction [72.05649682685197]
  State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views. This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints. Motivated by recent advances in the area of monocular geometry prediction, we explore the utility these cues provide for improving neural implicit surface reconstruction.
  arXiv  Detail & Related papers  (2022-06-01T17:58:15Z)
• PANDORA: Polarization-Aided Neural Decomposition Of Radiance [20.760987175553655]
  Inverse rendering is a fundamental problem in computer graphics and vision. Recent progress in representing scene properties as coordinate-based neural networks have facilitated neural inverse rendering. We propose PANDORA, a polarimetric inverse rendering approach based on implicit neural representations.
  arXiv  Detail & Related papers  (2022-03-25T05:41:52Z)
• Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo [103.08512487830669]
  We present a modern solution to the multi-view photometric stereo problem (MVPS) We procure the surface orientation using a photometric stereo (PS) image formation model and blend it with a multi-view neural radiance field representation to recover the object's surface geometry. Our method performs neural rendering of multi-view images while utilizing surface normals estimated by a deep photometric stereo network.
  arXiv  Detail & Related papers  (2021-10-11T20:20:03Z)
• Deep Polarization Imaging for 3D shape and SVBRDF Acquisition [7.86578678811226]
  We present a novel method for efficient acquisition of shape and spatially varying reflectance of 3D objects using polarization cues. Unlike previous works that have exploited polarization to estimate material or object appearance under certain constraints, we lift such restrictions by coupling polarization imaging with deep learning. We demonstrate our approach to achieve superior results compared to recent works employing deep learning in conjunction with flash illumination.
  arXiv  Detail & Related papers  (2021-05-06T17:58:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.