mlsanityData to 7 Oct 2026

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

arXiv 1907.10326 ↗First posted 24 Jul 2019cs.CVcited by 379

Not on the map. Why?

Cited by 32 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress with plausible results. The convolutional neural networks are generally composed of two parts: an encoder for dense feature extraction and a decoder for predicting the desired depth. In the encoder-decoder schemes, repeated strided convolution and spatial pooling layers lower the spatial resolution of transitional outputs, and several techniques such as skip connections or multi-layer deconvolutional networks are adopted to recover the original resolution for effective dense prediction. In this paper, for more effective guidance of densely encoded features to the desired depth prediction, we propose a network architecture that utilizes novel local planar guidance layers located at multiple stages in the decoding phase. We show that the proposed method outperforms the state-of-the-art works with significant margin evaluating on challenging benchmarks. We also provide results from an ablation study to validate the effectiveness of the proposed method.

Key facts. Cited by 379 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 65; 2022: 86; 2023: 79; 2024: 73; 2025: 45; 2026: 31.

379 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  3. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  4. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  5. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  6. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  7. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  8. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  9. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  10. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  11. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  12. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
38 more
  1. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  2. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  3. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 163
  4. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  5. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  6. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  7. 2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 119
  8. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  9. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  10. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  11. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  12. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  13. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  14. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  15. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  16. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  17. 2023DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimationcited by 81
  18. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  19. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  20. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  21. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  22. 2022Can Language Understand Depth?cited by 66
  23. 2021Ground-aware Monocular 3D Object Detection for Autonomous Drivingcited by 65
  24. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  25. 2021Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baselinecited by 61
  26. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 60
  27. 2022Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepthcited by 58
  28. 2023Robust Monocular Depth Estimation under Challenging Conditionscited by 58
  29. 2023Learning to Upsample by Learning to Samplecited by 57
  30. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  31. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  32. 2023IEBins: Iterative Elastic Bins for Monocular Depth Estimationcited by 53
  33. 2023All in Tokens: Unifying Output Space of Visual Tasks via Soft Tokencited by 52
  34. 2022Hierarchical Normalization for Robust Monocular Depth Estimationcited by 51
  35. 2021Radar-Camera Pixel Depth Association for Depth Completioncited by 49
  36. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  37. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  38. 2022Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detectioncited by 48

50 most cited of 379 All 379 (JSON)