Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon +2 more
3/22/2020
cs.CVcs.GRcs.LG

Official code: lioryariv/idr (738 stars, MIT, last commit 2021-07-05).

Abstract

In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates the light reflected from the surface towards the camera. The geometry is represented as a zero level-set of a neural network, while the neural renderer, derived from the rendering equation, is capable of (implicitly) modeling a wide set of lighting conditions and materials. We trained our network on real world 2D images of objects with different material properties, lighting conditions, and noisy camera initializations from the DTU MVS dataset. We found our model to produce state of the art 3D surface reconstructions with high fidelity, resolution and detail.

View on arXivView PDF

Code Implementations(1)

lioryariv/idrOfficial100%
MIT
73889Shell, PythonOct 4, 20205 years agoMIT

Similar Papers

NoPose-NeuS: Jointly Optimizing Camera Poses with Neural Implicit Surfaces for Multi-view Reconstruction

90% match2023

NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images

89% match1 repo5982023

NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation

88% match1 repo62023

PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo

88% match1 repo1392022

PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction

88% match1 repo292025

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

88% match1 repo1.8k2021

Cite this paper

@article{yariv2020multiview,
  title  = {Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance},
  author = {Lior Yariv and Yoni Kasten and Dror Moran and Meirav Galun and Matan Atzmon and Ronen Basri and Yaron Lipman},
  year   = {2020},
  eprint = {2003.09852},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2003.09852}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2003.09852.svg)](https://codeofpaper.com/paper/2003.09852)

Discussion