# StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation

arXiv: https://arxiv.org/abs/2108.08574 · HTML: https://mlsanity.com/paper/2108.08574/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 19 Aug 2021.

## Builds on (most cited first, 30 of 31)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [Learning to Recover 3D Scene Shape from a Single Image](https://mlsanity.com/paper/2012.09365/) (2020)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries](https://mlsanity.com/paper/1803.08673/) (2018)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Evaluation of CNN-based Single-Image Depth Estimation Methods](https://mlsanity.com/paper/1805.01328/) (2018)
- [Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera](https://mlsanity.com/paper/1907.05820/) (2019)
- [3D Ken Burns Effect from a Single Image](https://mlsanity.com/paper/1909.05483/) (2019)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [FastDepth: Fast Monocular Depth Estimation on Embedded Systems](https://mlsanity.com/paper/1903.03273/) (2019)
- [InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset](https://mlsanity.com/paper/1809.00716/) (2018)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [Designing Deep Networks for Surface Normal Estimation](https://mlsanity.com/paper/1411.4958/) (2014)
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://mlsanity.com/paper/1902.09777/) (2019)
- [LEGO: Learning Edge with Geometry all at Once by Watching Videos](https://mlsanity.com/paper/1803.05648/) (2018)
- [P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation](https://mlsanity.com/paper/2007.07696/) (2020)
- [Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments](https://mlsanity.com/paper/1910.08898/) (2019)
- [Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding](https://mlsanity.com/paper/1806.10556/) (2018)
- [Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields](https://mlsanity.com/paper/1603.06359/) (2016)
- [Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environments](https://mlsanity.com/paper/1703.07334/) (2017)
- [StructVIO : Visual-inertial Odometry with Structural Regularity of Man-made Environments](https://mlsanity.com/paper/1810.06796/) (2018)
- [TextSLAM: Visual SLAM with Planar Text Features](https://mlsanity.com/paper/1912.05002/) (2019)

## Built on by (most cited first, 30 of 36)

- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation](https://mlsanity.com/paper/2203.14211/) (2022)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [Towards Zero-Shot Scale-Aware Monocular Depth Estimation](https://mlsanity.com/paper/2306.17253/) (2023)
- [iDisc: Internal Discretization for Monocular Depth Estimation](https://mlsanity.com/paper/2304.06334/) (2023)
- [NDDepth: Normal-Distance Assisted Monocular Depth Estimation](https://mlsanity.com/paper/2309.10592/) (2023)
- [Toward Practical Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2112.02306/) (2021)
- [WorDepth: Variational Language Prior for Monocular Depth Estimation](https://mlsanity.com/paper/2404.03635/) (2024)
- [StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints](https://mlsanity.com/paper/2209.05277/) (2022)
- [PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting](https://mlsanity.com/paper/2412.12096/) (2024)
- [RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions](https://mlsanity.com/paper/2410.02924/) (2024)
- [ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation](https://mlsanity.com/paper/2407.08187/) (2024)
- [GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes](https://mlsanity.com/paper/2309.16019/) (2023)
- [Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following](https://mlsanity.com/paper/2304.03767/) (2023)
- [NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion](https://mlsanity.com/paper/2311.07166/) (2023)
- [A Surface-normal Based Neural Framework for Colonoscopy Reconstruction](https://mlsanity.com/paper/2303.07264/) (2023)
- [ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction](https://mlsanity.com/paper/2111.10371/) (2021)
- [RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion](https://mlsanity.com/paper/2306.03584/) (2023)
- [Deeper into Self-Supervised Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2312.01283/) (2023)
- [MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views](https://mlsanity.com/paper/2404.06753/) (2024)
- [AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization](https://mlsanity.com/paper/2308.10001/) (2023)
- [Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction](https://mlsanity.com/paper/2305.07269/) (2023)
- [GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints](https://mlsanity.com/paper/2402.14354/) (2024)
- [P2SDF for Neural Indoor Scene Reconstruction](https://mlsanity.com/paper/2303.00236/) (2023)
- [Background Prompting for Improved Object Depth](https://mlsanity.com/paper/2306.05428/) (2023)
- [SemHint-MD: Learning from Noisy Semantic Labels for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2303.18219/) (2023)
- [InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation](https://mlsanity.com/paper/2309.13516/) (2023)
- [Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization](https://mlsanity.com/paper/2409.02486/) (2024)
- [PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors](https://mlsanity.com/paper/2510.23930/) (2025)

## Abstract (arXiv)

Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the lack of textures. Without rich textures, the photometric consistency is too weak to train a good depth network. Inspired by the early works on indoor modeling, we leverage the structural regularities exhibited in indoor scenes, to train a better depth network. Specifically, we adopt two extra supervisory signals for self-supervised training: 1) the Manhattan normal constraint and 2) the co-planar constraint. The Manhattan normal constraint enforces the major surfaces (the floor, ceiling, and walls) to be aligned with dominant directions. The co-planar constraint states that the 3D points be well fitted by a plane if they are located within the same planar region. To generate the supervisory signals, we adopt two components to classify the major surface normal into dominant directions and detect the planar regions on the fly during training. As the predicted depth becomes more accurate after more training epochs, the supervisory signals also improve and in turn feedback to obtain a better depth model. Through extensive experiments on indoor benchmark datasets, the results show that our network outperforms the state-of-the-art methods. The source code is available at https://github.com/SJTU-ViSYS/StructDepth .