mlsanityData to 7 Oct 2026

NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion

arXiv 2311.07166 ↗First posted 13 Nov 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel physics (geometry)-driven deep learning frameworks for these two tasks by assuming that 3D scenes are constituted with piece-wise planes. Instead of directly estimating the depth map or completing the sparse depth map, we propose to estimate the surface normal and plane-to-origin distance maps or complete the sparse surface normal and distance maps as intermediate outputs. To this end, we develop a normal-distance head that outputs pixel-level surface normal and distance. Meanwhile, the surface normal and distance maps are regularized by a developed plane-aware consistency constraint, which are then transformed into depth maps. Furthermore, we integrate an additional depth head to strengthen the robustness of the proposed frameworks. Extensive experiments on the NYU-Depth-v2, KITTI and SUN RGB-D datasets demonstrate that our method exceeds in performance prior state-of-the-art monocular depth estimation and completion competitors. The source code will be available at https://github.com/ShuweiShao/NDDepth.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 64 of its 95 references that are in the map. First posted on arXiv 13 Nov 2023.

Builds on

64 of 95 references.

References · 64

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  8. 2021Vision Transformers for Dense Predictioncited by 1,789
  9. 2017Deformable Convolutional Networkscited by 1,481
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  11. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  12. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
38 more
  1. 2017Deep Mutual Learningcited by 621
  2. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  3. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  4. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  5. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  6. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  7. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  8. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  9. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  10. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  11. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  12. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  13. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  14. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  15. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  16. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  17. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  18. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  19. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  20. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  21. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  22. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  23. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  24. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  25. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  26. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 92
  27. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  28. 2015The Fast Bilateral Solvercited by 86
  29. 2020Guiding Monocular Depth Estimation Using Depth-Attention Volumecited by 82
  30. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  31. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  32. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  33. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  34. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 70
  35. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  36. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  37. 2014Designing Deep Networks for Surface Normal Estimationcited by 59
  38. 2019Structure-Aware Residual Pyramid Network for Monocular Depth Estimationcited by 49

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 2.

8 papers.

  1. 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimationcited by 20
  2. 2024Scene Prior Filtering for Depth Super-Resolutioncited by 5
  3. 2025Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequencescited by 5
  4. 2025DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereocited by 3
  5. 2025FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusioncited by 0
  6. 2025Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learningcited by 0
  7. 2026Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusioncited by 0
  8. 2026Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimationcited by 0