# NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction arXiv: https://arxiv.org/abs/2210.06853 ยท HTML: https://mlsanity.com/paper/2210.06853/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 67 of its 93 references that are in the map. - First posted on arXiv 13 Oct 2022. ## Builds on (most cited first, 30 of 67) - [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019) - [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022) - [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017) - [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019) - [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018) - [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021) - [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021) - [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021) - [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022) - [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021) - [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020) - [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020) - [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019) - [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018) - [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020) - [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021) - [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022) - [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018) - [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019) - [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021) - [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021) - [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016) - [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020) - [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022) - [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022) - [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019) - [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019) - [Dense Depth Priors for Neural Radiance Fields from Sparse Input Views](https://mlsanity.com/paper/2112.03288/) (2021) - [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019) - [Learning Shape Templates with Structured Implicit Functions](https://mlsanity.com/paper/1904.06447/) (2019) ## Built on by (most cited first, 5 of 5) - [VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization](https://mlsanity.com/paper/2303.17968/) (2023) - [PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields](https://mlsanity.com/paper/2401.00871/) (2023) - [Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints](https://mlsanity.com/paper/2309.09739/) (2023) - [FAWN: Floor-And-Walls Normal Regularization for Direct Neural TSDF Reconstruction](https://mlsanity.com/paper/2406.12054/) (2024) - [HAFMat: Hybrid Priors Guided Adaptive Fusion for Single-Image Human Material Estimation](https://mlsanity.com/paper/2606.16323/) (2026) ## Abstract (arXiv) We present a novel neural surface reconstruction method called NeuralRoom for reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit neural representations have become a promising way to reconstruct surfaces from multiview images due to their high-quality results and simplicity. However, implicit neural representations usually cannot reconstruct indoor scenes well because they suffer severe shape-radiance ambiguity. We assume that the indoor scene consists of texture-rich and flat texture-less regions. In texture-rich regions, the multiview stereo can obtain accurate results. In the flat area, normal estimation networks usually obtain a good normal estimation. Based on the above observations, we reduce the possible spatial variation range of implicit neural surfaces by reliable geometric priors to alleviate shape-radiance ambiguity. Specifically, we use multiview stereo results to limit the NeuralRoom optimization space and then use reliable geometric priors to guide NeuralRoom training. Then the NeuralRoom would produce a neural scene representation that can render an image consistent with the input training images. In addition, we propose a smoothing method called perturbation-residual restrictions to improve the accuracy and completeness of the flat region, which assumes that the sampling points in a local surface should have the same normal and similar distance to the observation center. Experiments on the ScanNet dataset show that our method can reconstruct the texture-less area of indoor scenes while maintaining the accuracy of detail. We also apply NeuralRoom to more advanced multiview reconstruction algorithms and significantly improve their reconstruction quality.