mlsanityData to 14 Oct 2026

CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

arXiv 1904.02028 ↗First posted 3 Apr 2019cs.CVcited by 75

Not on the map. Why?

Abstract (arXiv)

Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 10; 2023: 15; 2024: 14; 2025: 12; 2026: 4.

75 papers.

Sort:

By area:

  1. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  2. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  3. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  4. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  5. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
  6. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  7. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 124
  8. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  9. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 101
  10. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 101
  11. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 84
  12. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
38 more
  1. 2021Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraintscited by 81
  2. 2025PromptHMR: Promptable Human Mesh Recoverycited by 76
  3. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  4. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  5. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  6. 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 34
  7. 2021PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Losscited by 31
  8. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  9. 2023Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Modelcited by 29
  10. 2023Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-Viewcited by 27
  11. 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
  12. 2021Defocus Map Estimation and Deblurring from a Single Dual-Pixel Imagecited by 25
  13. 2025Multi-view Reconstruction via SfM-guided Monocular Depth Estimationcited by 20
  14. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 18
  15. 2023LightDepth: Single-View Depth Self-Supervision from Illumination Declinecited by 17
  16. 2024SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokenscited by 16
  17. 2021Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimationcited by 14
  18. 2023G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Datacited by 13
  19. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
  20. 2023Aberration-Aware Depth-from-Focuscited by 12
  21. 2023The Second Monocular Depth Estimation Challengecited by 12
  22. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  23. 2022FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutionscited by 11
  24. 2022SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networkscited by 10
  25. 2021Radar Camera Fusion via Representation Learning in Autonomous Drivingcited by 9
  26. 2023Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasingcited by 9
  27. 2021CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameterscited by 8
  28. 2025LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoningcited by 8
  29. 2021Lightweight Monocular Depth with a Novel Neural Architecture Search Methodcited by 7
  30. 2021NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesiscited by 7
  31. 2024Towards Cross-View-Consistent Self-Supervised Surround Depth Estimationcited by 7
  32. 2022A Light Touch Approach to Teaching Transformers Multi-view Geometrycited by 6
  33. 2023MonoEdge: Monocular 3D Object Detection Using Local Perspectivescited by 6
  34. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 6
  35. 2021Instant Visual Odometry Initialization for Mobile ARcited by 5
  36. 2022Automated Distance Estimation for Wildlife Camera Trappingcited by 5
  37. 2024Convolution kernel adaptation to calibrated fisheyecited by 5
  38. 2021Overcoming the Distance Estimation Bottleneck in Estimating Animal Abundance with Camera Trapscited by 4

50 most cited of 75 All 75 (JSON)