mlsanityData to 7 Oct 2026

3D Packing for Self-Supervised Monocular Depth Estimation

arXiv 1905.02693 ↗First posted 6 May 2019cs.CV cs.LG cs.ROcited by 437

Not on the map. Why?

Abstract (arXiv)

Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. The 3D inductive bias in PackNet enables it to scale with input resolution and number of parameters without overfitting, generalizing better on out-of-domain data such as the NuScenes dataset. Furthermore, it does not require large-scale supervised pretraining on ImageNet and can run in real-time. Finally, we release DDAD (Dense Depth for Automated Driving), a new urban driving dataset with more challenging and accurate depth evaluation, thanks to longer-range and denser ground-truth depth generated from high-density LiDARs mounted on a fleet of self-driving cars operating world-wide.

Key facts. Cited by 437 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 65; 2022: 85; 2023: 101; 2024: 79; 2025: 49; 2026: 58.

437 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  3. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  4. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  5. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  6. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  7. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  8. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  9. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  10. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  11. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  12. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 297
38 more
  1. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  2. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  3. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  4. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  5. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  6. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  7. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  8. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  9. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  10. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  11. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  12. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 116
  13. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  14. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  15. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  16. 2023CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perceptioncited by 81
  17. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  18. 2024DepthFM: Fast Monocular Depth Estimation with Flow Matchingcited by 76
  19. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  20. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  21. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  22. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  23. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  24. 2022CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformercited by 66
  25. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  26. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  27. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  28. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  29. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  30. 2023Robust Monocular Depth Estimation under Challenging Conditionscited by 58
  31. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  32. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  33. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  34. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  35. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  36. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  37. 2024GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splattingcited by 50
  38. 2021Radar-Camera Pixel Depth Association for Depth Completioncited by 49

50 most cited of 437 All 437 (JSON)