mlsanityData to 14 Oct 2026

NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis

arXiv 2112.12577 ↗First posted 22 Dec 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Building upon the recent progress in novel view synthesis, we propose its application to improve monocular depth estimation. In particular, we propose a novel training method split in three main steps. First, the prediction results of a monocular depth network are warped to an additional view point. Second, we apply an additional image synthesis network, which corrects and improves the quality of the warped RGB image. The output of this network is required to look as similar as possible to the ground-truth view by minimizing the pixel-wise RGB reconstruction error. Third, we reapply the same monocular depth estimation onto the synthesized second view point and ensure that the depth predictions are consistent with the associated ground truth depth. Experimental results prove that our method achieves state-of-the-art or comparable performance on the KITTI and NYU-Depth-v2 datasets with a lightweight and simple vanilla U-Net architecture.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 42 of its 78 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

42 of 78 references.

References · 42

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  12. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
30 more
  1. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  2. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  3. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  4. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  5. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  6. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
  7. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  8. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
  9. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  10. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  11. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  12. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 145
  13. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  14. 20193D Ken Burns Effect from a Single Imagecited by 128
  15. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  16. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  17. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  18. 2018InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Datasetcited by 87
  19. 2020Guiding Monocular Depth Estimation Using Depth-Attention Volumecited by 82
  20. 2018Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimationcited by 78
  21. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  22. 2017Transformation-Grounded Image Generation Network for Novel 3D View Synthesiscited by 59
  23. 2019SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimationcited by 59
  24. 2019Structure-Aware Residual Pyramid Network for Monocular Depth Estimationcited by 49
  25. 2016Stacked Generative Adversarial Networkscited by 44
  26. 2018Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networkscited by 31
  27. 2020On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigationcited by 17
  28. 2019Depth Extraction from Video Using Non-parametric Samplingcited by 11
  29. 2017Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inferencecited by 5
  30. 2016A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Imagescited by 1

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 2; 2025: 1.

7 papers.

  1. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  2. 2022Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimationcited by 8
  3. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 6
  4. 2024NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimationcited by 2
  5. 2024Geometric Constraints in Deep Learning Frameworks: A Surveycited by 1
  6. 2022Deep Camera Pose Regression Using Pseudo-LiDARcited by 0
  7. 2023Depth self-supervision for single image novel view synthesiscited by 0