mlsanityData to 7 Oct 2026

Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

arXiv 2007.10603 ↗First posted 21 Jul 2020cs.CVcited by 140

Not on the map. Why?

Abstract (arXiv)

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for pixels in textureless regions or multiple local minima for less discriminative pixels. In this work, feature-metric loss is proposed and defined on feature representation, where the feature representation is also learned in a self-supervised manner and regularized by both first-order and second-order derivatives to constrain the loss landscapes to form proper convergence basins. Comprehensive experiments and detailed analysis via visualization demonstrate the effectiveness of the proposed feature-metric loss. In particular, our method improves state-of-the-art methods on KITTI from 0.885 to 0.925 measured by δ1 for depth estimation, and significantly outperforms previous method for visual odometry.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 35; 2023: 36; 2024: 20; 2025: 6; 2026: 6.

140 papers.

Sort:

By area:

  1. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  2. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  3. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  4. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  5. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  6. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  7. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  8. 2021Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescuecited by 70
  9. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  10. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  11. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  12. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
38 more
  1. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  2. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  3. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  4. 2022Hierarchical Normalization for Robust Monocular Depth Estimationcited by 51
  5. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
  6. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  7. 2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
  8. 2021Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometrycited by 46
  9. 2021StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationcited by 36
  10. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  11. 2021Geometric Unsupervised Domain Adaptation for Semantic Segmentationcited by 33
  12. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
  13. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  14. 2024Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Drivingcited by 30
  15. 2021Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimationcited by 27
  16. 2022DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completioncited by 27
  17. 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
  18. 2021Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 25
  19. 2022When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimationcited by 24
  20. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  21. 2022DevNet: Self-supervised Monocular Depth Learning via Density Volume Constructioncited by 22
  22. 2023Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVcited by 21
  23. 2023SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimationcited by 21
  24. 2022Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamicscited by 20
  25. 2021Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidancecited by 19
  26. 2022Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Mattercited by 18
  27. 2023MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervisioncited by 18
  28. 2022Depth Field Networks for Generalizable Multi-view Scene Representationcited by 17
  29. 2022Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimationcited by 17
  30. 2023LightDepth: Single-View Depth Self-Supervision from Illumination Declinecited by 17
  31. 2023EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimationcited by 16
  32. 2023DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibriumcited by 16
  33. 2021Adversarial Attacks on Multi-task Visual Perception for Autonomous Drivingcited by 14
  34. 2022Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motioncited by 14
  35. 2023Learnable Differencing Center for Nighttime Depth Perceptioncited by 14
  36. 2021Advancing Self-supervised Monocular Depth Learning with Sparse LiDARcited by 13
  37. 2022The Monocular Depth Estimation Challengecited by 13
  38. 2023From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Priorcited by 13

50 most cited of 140 All 140 (JSON)