# Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

arXiv: https://arxiv.org/abs/2003.09852 · HTML: https://mlsanity.com/paper/2003.09852/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision](https://mlsanity.com/paper/2303.09554/) (2023)
- [SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration](https://mlsanity.com/paper/2208.10449/) (2022)
- [Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation](https://mlsanity.com/paper/2504.18509/) (2025)
- [SegNeRF: 3D Part Segmentation with Neural Radiance Fields](https://mlsanity.com/paper/2211.11215/) (2022)
- [αSurf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity](https://mlsanity.com/paper/2303.10083/) (2023)
- [ObjectCarver: Semi-automatic segmentation, reconstruction and separation of 3D objects](https://mlsanity.com/paper/2407.19108/) (2024)

## Abstract (arXiv)

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.