mlsanityData to 7 Oct 2026

MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments

arXiv 2107.12429 ↗First posted 26 Jul 2021cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Self-supervised depth estimation for indoor environments is more challenging than its outdoor counterpart in at least the following two aspects: (i) the depth range of indoor sequences varies a lot across different frames, making it difficult for the depth network to induce consistent depth cues, whereas the maximum distance in outdoor scenes mostly stays the same as the camera usually sees the sky; (ii) the indoor sequences contain much more rotational motions, which cause difficulties for the pose network, while the motions of outdoor sequences are pre-dominantly translational, especially for driving datasets such as KITTI. In this paper, special considerations are given to those challenges and a set of good practices are consolidated for improving the performance of self-supervised monocular depth estimation in indoor environments. The proposed method mainly consists of two novel modules, ie, a depth factorization module and a residual pose estimation module, each of which is designed to respectively tackle the aforementioned challenges. The effectiveness of each module is shown through a carefully conducted ablation study and the demonstration of the state-of-the-art performance on three indoor datasets, ie, EuRoC, NYUv2, and 7-scenes.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

34 of 50 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Non-local Neural Networkscited by 2,290
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  6. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  7. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  8. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  10. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  11. 2018Pyramid Stereo Matching Networkcited by 486
  12. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
22 more
  1. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  2. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  3. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  4. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  5. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  6. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  7. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  8. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  9. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  10. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  11. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  12. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  13. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  14. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  15. 2019DepthTransfer: Depth Extraction from Video Using Non-parametric Samplingcited by 60
  16. 2019Visual Odometry Revisited: What Should Be Learnt?cited by 57
  17. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  18. 2020Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Predictioncited by 41
  19. 2020P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimationcited by 41
  20. 2020Learning Monocular Visual Odometry via Self-Supervised Long-Term Modelingcited by 39
  21. 2019Moving Indoor: Unsupervised Video Depth Learning in Challenging Environmentscited by 31
  22. 2016Depth from a Single Image by Harmonizing Overcomplete Local Network Predictionscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 18; 2023: 9; 2024: 6; 2025: 1; 2026: 2.

38 papers.

Sort:

By area:

  1. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  2. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  3. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  4. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  5. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  6. 2024WorDepth: Variational Language Prior for Monocular Depth Estimationcited by 34
  7. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
  8. 2022PlaneMVS: 3D Plane Reconstruction from Multi-View Stereocited by 29
  9. 2022DevNet: Self-supervised Monocular Depth Learning via Density Volume Constructioncited by 22
  10. 2022NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstructioncited by 21
  11. 2022Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problemcited by 20
  12. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 20
26 more
  1. 2022Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimationcited by 17
  2. 2023Fully Self-Supervised Depth Estimation from Defocus Cluecited by 17
  3. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  4. 2022Event-based Monocular Dense Depth Estimation with Recurrent Transformerscited by 13
  5. 2023GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenescited by 13
  6. 2022RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereocited by 12
  7. 2022MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 12
  8. 2022A Survey on RGB-D Datasetscited by 11
  9. 2023Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Followingcited by 9
  10. 2022GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mappingcited by 8
  11. 2021ColDE: A Depth Estimation Framework for Colonoscopy Reconstructioncited by 7
  12. 2023Deeper into Self-Supervised Monocular Indoor Depth Estimationcited by 7
  13. 2024MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Viewscited by 6
  14. 2025Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimationcited by 6
  15. 2023AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimizationcited by 4
  16. 2022FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Camerascited by 3
  17. 2023Meta-Optimization for Higher Model Generalizability in Single-Image Depth Predictioncited by 3
  18. 2024GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraintscited by 3
  19. 2022Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depthcited by 2
  20. 2022Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agentscited by 1
  21. 2023InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimationcited by 1
  22. 2024Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometrycited by 1
  23. 2022CNN-Augmented Visual-Inertial SLAM with Planar Constraintscited by 0
  24. 2022Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimationcited by 0
  25. 2026Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimationcited by 0
  26. 2026Monocular Depth Estimation from a Single Image: Progress and Opportunitiescited by 0