mlsanityData to 14 Oct 2026

PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

arXiv 2312.02284 ↗First posted 4 Dec 2023cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and devices. Existing high-resolution strategies show promise, but they often face limitations, ranging from error propagation to the loss of high-frequency details. We present PatchFusion, a novel tile-based framework with three key components to improve the current state of the art: (1) A patch-wise fusion network that fuses a globally-consistent coarse prediction with finer, inconsistent tiled predictions via high-level feature guidance, (2) A Global-to-Local (G2L) module that adds vital context to the fusion network, discarding the need for patch selection heuristics, and (3) A Consistency-Aware Training (CAT) and Inference (CAI) approach, emphasizing patch overlap consistency and thereby eradicating the necessity for post-processing. Experiments on UnrealStereo4K, MVS-Synth, and Middleburry 2014 demonstrate that our framework can generate high-resolution depth maps with intricate details. PatchFusion is independent of the base model for depth estimation. Notably, our framework built on top of SOTA ZoeDepth brings improvements for a total of 17.3% and 29.4% in terms of the root mean squared error (RMSE) on UnrealStereo4K and MVS-Synth, respectively.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 30 of its 47 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

30 of 47 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2017Mask R-CNNcited by 7,277
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  8. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  11. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  12. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
18 more
  1. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  2. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  3. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  4. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 269
  5. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 168
  6. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  7. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  8. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 118
  9. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  10. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 73
  11. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72
  12. 2021Discrete Cosine Transform Network for Guided Depth Map Super-Resolutioncited by 71
  13. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  14. 2023All in Tokens: Unifying Output Space of Visual Tasks via Soft Tokencited by 52
  15. 2022Guided Depth Super-Resolution by Deep Anisotropic Diffusioncited by 46
  16. 2022Learning Graph Regularisation for Guided Super-Resolutioncited by 27
  17. 2023Guided Depth Map Super-resolution: A Surveycited by 23
  18. 2023Single Image Depth Prediction Made Better: A Multivariate Gaussian Takecited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 14; 2026: 15.

41 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,422
  2. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  3. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
  4. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  5. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  6. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  7. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 51
  8. 2024Video Depth without Video Modelscited by 29
  9. 2026InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fieldscited by 23
  10. 2024MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstructioncited by 18
  11. 2024PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimationcited by 16
  12. 2025Depth Anything at Any Conditioncited by 12
29 more
  1. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  2. 2026AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstructioncited by 9
  3. 2024Amodal Depth Anything: Amodal Depth Estimation in the Wildcited by 5
  4. 2025PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimationcited by 5
  5. 2024Scale-Invariant Monocular Depth Estimation via SSI Depthcited by 4
  6. 2024Self-Distilled Depth Refinement with Noisy Poisson Fusioncited by 4
  7. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  8. 2025From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarioscited by 3
  9. 2026DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimationcited by 3
  10. 2025Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguitycited by 2
  11. 2025One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Imagescited by 2
  12. 2025Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identificationcited by 2
  13. 2026Pixel-Perfect Visual Geometry Estimationcited by 2
  14. 2025PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusioncited by 1
  15. 2025Boosting Monocular Metric Depth Estimation via Bokeh Renderingcited by 1
  16. 2026Any Resolution Any Geometry: From Multi-View To Multi-Patchcited by 1
  17. 20262K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Predictioncited by 1
  18. 2026WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimationcited by 1
  19. 2026PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimationcited by 1
  20. 2024Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive Perspectivecited by 0
  21. 2024EDADepth: Enhanced Data Augmentation for Monocular Depth Estimationcited by 0
  22. 2025Survey on Monocular Metric Depth Estimationcited by 0
  23. 2025Back to the Future Cyclopean Stereo: a human perception approach combining deep and geometric constraintscited by 0
  24. 2026Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagerycited by 0
  25. 2026Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentationcited by 0
  26. 2026Monocular Depth Estimation from a Single Image: Progress and Opportunitiescited by 0
  27. 2026A Vision-Language Framework for Measuring Social Life on Sidewalkscited by 0
  28. 2026EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decodercited by 0
  29. 2026Learning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimatescited by 0