mlsanityData to 7 Oct 2026

PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation

arXiv 2110.05839 ↗First posted 12 Oct 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Unsupervised learning of depth from indoor monocular videos is challenging as the artificial environment contains many textureless regions. Fortunately, the indoor scenes are full of specific structures, such as planes and lines, which should help guide unsupervised depth learning. This paper proposes PLNet that leverages the plane and line priors to enhance the depth estimation. We first represent the scene geometry using local planar coefficients and impose the smoothness constraint on the representation. Moreover, we enforce the planar and linear consistency by randomly selecting some sets of points that are probably coplanar or collinear to construct simple and effective consistency losses. To verify the proposed method's effectiveness, we further propose to evaluate the flatness and straightness of the predicted point cloud on the reliable planar and linear regions. The regularity of these regions indicates quality indoor reconstruction. Experiments on NYU Depth V2 and ScanNet show that PLNet outperforms existing methods. The code is available at urlhttps://github.com/HalleyJiang/PLNet.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 34 of its 62 references that are in the map. First posted on arXiv 12 Oct 2021.

Builds on

34 of 62 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2015Spatial Transformer Networkscited by 1,423
  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. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  8. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  9. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  10. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  11. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  12. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
22 more
  1. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  2. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  3. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  4. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  5. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  6. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  7. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  8. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  9. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  10. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  11. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  12. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  13. 2018PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Imagecited by 77
  14. 2017Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimationcited by 70
  15. 2017PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segmentscited by 58
  16. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  17. 2019Single-Image Piece-wise Planar 3D Reconstruction via Associative Embeddingcited by 56
  18. 2020P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimationcited by 41
  19. 2019Moving Indoor: Unsupervised Video Depth Learning in Challenging Environmentscited by 31
  20. 2021Boosting Light-Weight Depth Estimation Via Knowledge Distillationcited by 16
  21. 2020DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videoscited by 10
  22. 2021Unsupervised Monocular Depth Perception: Focusing on Moving Objectscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 6; 2024: 1.

12 papers.

  1. 2022Can Language Understand Depth?cited by 66
  2. 2022StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hintscited by 28
  3. 2022Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAMcited by 10
  4. 2023SparseDC: Depth Completion from sparse and non-uniform inputscited by 8
  5. 2023Deeper into Self-Supervised Monocular Indoor Depth Estimationcited by 7
  6. 2022NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstructioncited by 5
  7. 2022Dense Depth Distillation with Out-of-Distribution Simulated Imagescited by 4
  8. 2023Meta-Optimization for Higher Model Generalizability in Single-Image Depth Predictioncited by 3
  9. 2023Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimationcited by 2
  10. 2023InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimationcited by 1
  11. 2023Deep Planar Parallax for Monocular Depth Estimationcited by 0
  12. 2024InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depthcited by 0