mlsanityData to 7 Oct 2026

Deep Planar Parallax for Monocular Depth Estimation

arXiv 2301.03178 ↗First posted 9 Jan 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth analysis reveals that utilizing flow-pretrain can optimize the network's usage of consecutive frame modeling, leading to substantial performance enhancement. Additionally, we propose Planar Position Embedding (PPE) to handle dynamic objects that defy static scene assumptions and to tackle slope variations that are challenging to differentiate. Comprehensive experiments on autonomous driving datasets, namely KITTI and the Waymo Open Dataset (WOD), prove that our Planar Parallax Network (PPNet) significantly surpasses existing learning-based methods in performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 78 references that are in the map. First posted on arXiv 9 Jan 2023.

Builds on

52 of 78 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2021Vision Transformers for Dense Predictioncited by 1,789
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  8. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  9. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  11. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
38 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  3. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  4. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  5. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  6. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  7. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  8. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  9. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  10. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  11. 2020Consistent Video Depth Estimationcited by 220
  12. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  13. 2020Robust Consistent Video Depth Estimationcited by 188
  14. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  15. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  16. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  17. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  18. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  19. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  20. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  21. 2020MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Maskcited by 117
  22. 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
  23. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  24. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  25. 2019DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registrationcited by 77
  26. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  27. 2019LO-Net: Deep Real-time Lidar Odometrycited by 59
  28. 2020Multi-view Depth Estimation using Epipolar Spatio-Temporal Networkscited by 59
  29. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  30. 2021DeepI2P: Image-to-Point Cloud Registration via Deep Classificationcited by 58
  31. 2019Visual Odometry Revisited: What Should Be Learnt?cited by 57
  32. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
  33. 2021Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometrycited by 46
  34. 2022Monocular 3D Object Detection with Depth from Motioncited by 38
  35. 2020PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimizationcited by 34
  36. 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
  37. 2020DMLO: Deep Matching LiDAR Odometrycited by 20
  38. 2021PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimationcited by 12

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.