mlsanityData to 7 Oct 2026

Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV

arXiv 2307.10713 ↗First posted 20 Jul 2023cs.CV cs.AI cs.ROcited by 21

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth estimation (SS-MDE) has the potential to scale to vast quantities of data. Unfortunately, existing approaches limit themselves to the automotive domain, resulting in models incapable of generalizing to complex environments such as natural or indoor settings. To address this, we propose a large-scale SlowTV dataset curated from YouTube, containing an order of magnitude more data than existing automotive datasets. SlowTV contains 1.7M images from a rich diversity of environments, such as worldwide seasonal hiking, scenic driving and scuba diving. Using this dataset, we train an SS-MDE model that provides zero-shot generalization to a large collection of indoor/outdoor datasets. The resulting model outperforms all existing SSL approaches and closes the gap on supervised SoTA, despite using a more efficient architecture. We additionally introduce a collection of best-practices to further maximize performance and zero-shot generalization. This includes 1) aspect ratio augmentation, 2) camera intrinsic estimation, 3) support frame randomization and 4) flexible motion estimation. Code is available at https://github.com/jspenmar/slowtv_monodepth.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 63 of its 80 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

63 of 80 references.

References · 63

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  9. 2021Vision Transformers for Dense Predictioncited by 1,789
  10. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  11. 2015Spatial Transformer Networkscited by 1,423
  12. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
38 more
  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  2. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  3. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  4. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  5. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  6. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  7. 2016Direct Sparse Odometrycited by 479
  8. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  9. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  10. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  11. 2017Sparsity Invariant CNNscited by 325
  12. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  13. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 236
  14. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  15. 2020Consistent Video Depth Estimationcited by 220
  16. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  17. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 188
  18. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  19. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  20. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  21. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  22. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  23. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  24. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  25. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  26. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  27. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  28. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  29. 2019Self-Supervised Monocular Depth Hintscited by 127
  30. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  31. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  32. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  33. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  34. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  35. 2018Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometrycited by 85
  36. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  37. 2018SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimationcited by 64
  38. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 13; 2025: 4; 2026: 1.

21 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  3. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 62
  4. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  5. 2024Depth Prompting for Sensor-Agnostic Depth Estimationcited by 26
  6. 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 25
  7. 2023Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Samplingcited by 19
  8. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  9. 2024The Third Monocular Depth Estimation Challengecited by 10
  10. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  11. 2024Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVcited by 7
  12. 2024CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentationcited by 6
9 more
  1. 2025SAB3R: Semantic-Augmented Backbone in 3D Reconstructioncited by 6
  2. 2023Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimationcited by 3
  3. 2024UnDIVE: Generalized Underwater Video Enhancement Using Generative Priorscited by 3
  4. 2024NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-trainingcited by 2
  5. 2025Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research Agendacited by 2
  6. 2024Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometrycited by 1
  7. 2024Revisit Self-supervised Depth Estimation with Local Structure-from-Motioncited by 1
  8. 2025EvtSlowTV -- A Large and Diverse Dataset for Event-Based Depth Estimationcited by 1
  9. 20262K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Predictioncited by 0