mlsanityData to 13 Oct 2026

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

arXiv 2105.14021 ↗First posted 28 May 2021cs.CVcited by 104

Not on the map. Why?

Abstract (arXiv)

Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method builds on our analysis on how the input resolution and the scene structure affects depth estimation performance. We demonstrate that there is a trade-off between a consistent scene structure and the high-frequency details, and merge low- and high-resolution estimations to take advantage of this duality using a simple depth merging network. We present a double estimation method that improves the whole-image depth estimation and a patch selection method that adds local details to the final result. We demonstrate that by merging estimations at different resolutions with changing context, we can generate multi-megapixel depth maps with a high level of detail using a pre-trained model.

Key facts. Cited by 104 papers in the map (data through 13 Oct 2026). Builds on 35 of its 58 references that are in the map. First posted on arXiv 28 May 2021.

Builds on

35 of 58 references.

References · 35

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,516
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,490
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,269
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 732
  7. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 722
  8. 2018Taskonomy: Disentangling Task Transfer Learningcited by 633
  9. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  10. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  11. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  12. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
23 more
  1. 2016Single-Image Depth Perception in the Wildcited by 179
  2. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  3. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  4. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 138
  5. 20193D Ken Burns Effect from a Single Imagecited by 128
  6. 2019Self-Supervised Monocular Depth Hintscited by 127
  7. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  8. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  9. 2016High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesiscited by 90
  10. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  11. 2020Guiding Monocular Depth Estimation Using Depth-Attention Volumecited by 82
  12. 2020The Edge of Depth: Explicit Constraints between Segmentation and Depthcited by 72
  13. 2018Synthetic Depth-of-Field with a Single-Camera Mobile Phonecited by 71
  14. 2018T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Taskscited by 70
  15. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  16. 2020OASIS: A Large-Scale Dataset for Single Image 3D in the Wildcited by 62
  17. 2019Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Predictioncited by 44
  18. 2020Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fieldscited by 40
  19. 2020High-Resolution Deep Image Mattingcited by 36
  20. 2019Visualization of Convolutional Neural Networks for Monocular Depth Estimationcited by 24
  21. 2017What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?cited by 16
  22. 2019The capacity of feedforward neural networkscited by 14
  23. 2020Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasetscited by 14

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 7; 2022: 28; 2023: 32; 2024: 20; 2025: 14; 2026: 3.

104 papers.

Sort:

By area:

  1. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 468
  2. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 398
  3. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 255
  4. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  5. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  6. 2023WonderJourney: Going from Anywhere to Everywherecited by 157
  7. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  8. 2023Visual Prompt Multi-Modal Trackingcited by 142
  9. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  10. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 122
  11. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  12. 20243D Gaussian as a New Era: A Surveycited by 103
38 more
  1. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  2. 2022Learning to generate line drawings that convey geometry and semanticscited by 83
  3. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  4. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  5. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  6. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  7. 2023Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidarcited by 60
  8. 2023Intrinsic Image Decomposition via Ordinal Shadingcited by 53
  9. 2022Source-free Depth for Object Pop-outcited by 52
  10. 20233D generation on ImageNetcited by 47
  11. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  12. 2023PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimationcited by 41
  13. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  14. 2023On the Importance of Accurate Geometry Data for Dense 3D Vision Taskscited by 26
  15. 2023DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptationcited by 25
  16. 2022Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regressioncited by 18
  17. 2023MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervisioncited by 18
  18. 2024PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimationcited by 16
  19. 2022360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Networkcited by 15
  20. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  21. 2024EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splattingcited by 15
  22. 2025Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimatorcited by 15
  23. 2023Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Networkcited by 14
  24. 2021GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Networkcited by 12
  25. 2023The Second Monocular Depth Estimation Challengecited by 12
  26. 2023Object Segmentation by Mining Cross-Modal Semanticscited by 12
  27. 2022A Survey on RGB-D Datasetscited by 11
  28. 2022High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registrationcited by 11
  29. 2022Improving Fairness in Image Classification via Sketchingcited by 11
  30. 2023Intrinsic Harmonization for Illumination-Aware Compositingcited by 11
  31. 2022SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networkscited by 10
  32. 2023High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimationcited by 10
  33. 2024The Third Monocular Depth Estimation Challengecited by 10
  34. 2021THE Benchmark: Transferable Representation Learning for Monocular Height Estimationcited by 8
  35. 2022Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Compositioncited by 8
  36. 2022Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimationcited by 8
  37. 2022Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photographycited by 8
  38. 2023WildFusion: Learning 3D-Aware Latent Diffusion Models in View Spacecited by 8

50 most cited of 104 All 104 (JSON)