mlsanityData to 7 Oct 2026

DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

arXiv 1809.01649 ↗First posted 5 Sep 2018cs.CVcited by 148

Not on the map. Why?

Abstract (arXiv)

We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brightness constancy and spatial smoothness priors to train depth or flow models. In this paper, we propose to leverage geometric consistency as additional supervisory signals. Our core idea is that for rigid regions we can use the predicted scene depth and camera motion to synthesize 2D optical flow by backprojecting the induced 3D scene flow. The discrepancy between the rigid flow (from depth prediction and camera motion) and the estimated flow (from optical flow model) allows us to impose a cross-task consistency loss. While all the networks are jointly optimized during training, they can be applied independently at test time. Extensive experiments demonstrate that our depth and flow models compare favorably with state-of-the-art unsupervised methods.

Key facts. Cited by 148 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 35; 2023: 33; 2024: 20; 2025: 7; 2026: 7.

148 papers.

Sort:

By area:

  1. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  2. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  3. 2021Asymmetric Bilateral Motion Estimation for Video Frame Interpolationcited by 101
  4. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  5. 2021SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warpingcited by 74
  6. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  7. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  8. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  9. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  10. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  11. 2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
  12. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
38 more
  1. 2021Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walkcited by 39
  2. 2023OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environmentscited by 39
  3. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  4. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  5. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  6. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  7. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  8. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  9. 2021Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approachescited by 27
  10. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  11. 2022Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learningcited by 26
  12. 2022PVO: Panoptic Visual Odometrycited by 26
  13. 2021Defocus Map Estimation and Deblurring from a Single Dual-Pixel Imagecited by 25
  14. 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 25
  15. 2021Attentive and Contrastive Learning for Joint Depth and Motion Field Estimationcited by 24
  16. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  17. 2023BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolationcited by 23
  18. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
  19. 2023RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenescited by 22
  20. 2021Binary TTC: A Temporal Geofence for Autonomous Navigationcited by 20
  21. 2023Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenescited by 20
  22. 2025Zero-Shot Monocular Scene Flow Estimation in the Wildcited by 20
  23. 20223D Object Detection with a Self-supervised Lidar Scene Flow Backbonecited by 19
  24. 2021VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residualscited by 17
  25. 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
  26. 2023XVO: Generalized Visual Odometry via Cross-Modal Self-Trainingcited by 17
  27. 2025LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understandingcited by 17
  28. 2023DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibriumcited by 16
  29. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15
  30. 2024Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flowcited by 15
  31. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  32. 2022TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolationcited by 14
  33. 2023Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Networkcited by 14
  34. 2021Advancing Self-supervised Monocular Depth Learning with Sparse LiDARcited by 13
  35. 2021GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Networkcited by 12
  36. 2022MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 12
  37. 2023MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Modelcited by 12
  38. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 12

50 most cited of 148 All 148 (JSON)