mlsanityData to 7 Oct 2026

PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation

arXiv 2406.06679 ↗First posted 10 Jun 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

This paper introduces PatchRefiner, an advanced framework for metric single image depth estimation aimed at high-resolution real-domain inputs. While depth estimation is crucial for applications such as autonomous driving, 3D generative modeling, and 3D reconstruction, achieving accurate high-resolution depth in real-world scenarios is challenging due to the constraints of existing architectures and the scarcity of detailed real-world depth data. PatchRefiner adopts a tile-based methodology, reconceptualizing high-resolution depth estimation as a refinement process, which results in notable performance enhancements. Utilizing a pseudo-labeling strategy that leverages synthetic data, PatchRefiner incorporates a Detail and Scale Disentangling (DSD) loss to enhance detail capture while maintaining scale accuracy, thus facilitating the effective transfer of knowledge from synthetic to real-world data. Our extensive evaluations demonstrate PatchRefiner's superior performance, significantly outperforming existing benchmarks on the Unreal4KStereo dataset by 18.1% in terms of the root mean squared error (RMSE) and showing marked improvements in detail accuracy and consistent scale estimation on diverse real-world datasets like CityScape, ScanNet++, and ETH3D.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 49 of its 71 references that are in the map. First posted on arXiv 10 Jun 2024.

Builds on

49 of 71 references.

References · 49

  1. 2017Mask R-CNNcited by 7,259
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  5. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  8. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  9. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  10. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  11. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  12. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
37 more
  1. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  2. 2020A Brief Review of Domain Adaptationcited by 287
  3. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  4. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  5. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  6. 2016Single-Image Depth Perception in the Wildcited by 179
  7. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  8. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  9. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 137
  10. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  11. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  12. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  13. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  14. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  15. 2021Discrete Cosine Transform Network for Guided Depth Map Super-Resolutioncited by 71
  16. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  17. 2018T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Taskscited by 70
  18. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  19. 2020Object Detection with a Unified Label Space from Multiple Datasetscited by 65
  20. 2014Fast Edge Detection Using Structured Forestscited by 64
  21. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  22. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  23. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  24. 2020Domain Adaptive Semantic Segmentation Using Weak Labelscited by 56
  25. 2018AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimationcited by 54
  26. 2022Guided Depth Super-Resolution by Deep Anisotropic Diffusioncited by 46
  27. 2023PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimationcited by 39
  28. 2021Self-supervised Learning of Depth Inference for Multi-view Stereocited by 28
  29. 2022Learning Graph Regularisation for Guided Super-Resolutioncited by 27
  30. 2020SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimationcited by 25
  31. 2020DESC: Domain Adaptation for Depth Estimation via Semantic Consistencycited by 25
  32. 2023Guided Depth Map Super-resolution: A Surveycited by 23
  33. 2022Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Trainingcited by 22
  34. 2023Single Image Depth Prediction Made Better: A Multivariate Gaussian Takecited by 14
  35. 2023The Second Monocular Depth Estimation Challengecited by 12
  36. 2023High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimationcited by 10
  37. 20223D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labelingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  2. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 73
  3. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  4. 2024Video Depth without Video Modelscited by 28
  5. 2024SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillationcited by 21
  6. 2025PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimationcited by 3
  7. 2025One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Imagescited by 2
  8. 2026Pixel-Perfect Visual Geometry Estimationcited by 2
  9. 2026EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VRcited by 2
  10. 2026UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decompositioncited by 1
  11. 2026PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimationcited by 1
  12. 2025Survey on Monocular Metric Depth Estimationcited by 0
3 more
  1. 2026Toward Real-World High-Precision Image Matting and Segmentationcited by 0
  2. 2026Any Resolution Any Geometry: From Multi-View To Multi-Patchcited by 0
  3. 20262K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Predictioncited by 0