mlsanityData to 7 Oct 2026

ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling

arXiv 2104.03560 ↗First posted 8 Apr 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We present an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network. Specifically, in the pyramid downsampling, we propose an Content Aware Pooling (CAP) module, which promotes local feature gathering by avoiding cross region pooling, so that the learned features become more representative. In the pyramid upsampling, we propose an Adaptive Flow Upsampling (AFU) module, where cross edge interpolation can be avoided, producing sharp motion boundaries. Equipped with these two modules, our method achieves the best performance for unsupervised optical flow estimation on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015. Particuarlly, we achieve EPE=1.5 on KITTI 2012 and F1=9.67% KITTI 2015, which outperform the previous state-of-the-art methods by 16.7% and 13.1%, respectively.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 66 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

31 of 66 references.

References · 31

  1. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  2. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  3. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  4. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  5. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  6. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  7. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  8. 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
  9. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  10. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  11. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  12. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
19 more
  1. 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
  2. 2019SelFlow: Self-Supervised Learning of Optical Flowcited by 128
  3. 2019Pixel-Adaptive Convolutional Neural Networkscited by 126
  4. 2020What Matters in Unsupervised Optical Flowcited by 124
  5. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  6. 2020MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Maskcited by 117
  7. 2016Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothnesscited by 101
  8. 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
  9. 2018Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimationcited by 94
  10. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  11. 2019DDFlow: Learning Optical Flow with Unlabeled Data Distillationcited by 63
  12. 2018Fast End-to-End Trainable Guided Filtercited by 50
  13. 2020Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimationcited by 49
  14. 2020LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimationcited by 37
  15. 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
  16. 2016Optical Flow with Semantic Segmentation and Localized Layerscited by 21
  17. 2016Unsupervised convolutional neural networks for motion estimationcited by 12
  18. 2020OccInpFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learningcited by 7
  19. 2019Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Datacited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 1; 2025: 1.

8 papers.

  1. 2023Learning Optical Flow from Event Camera with Rendered Datasetcited by 26
  2. 2022RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videoscited by 22
  3. 2023GAFlow: Incorporating Gaussian Attention into Optical Flowcited by 18
  4. 2022MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillationcited by 10
  5. 2023GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learningcited by 10
  6. 2023Supervised Homography Learning with Realistic Dataset Generationcited by 6
  7. 2024Deep Common Feature Mining for Efficient Video Semantic Segmentationcited by 4
  8. 2025CodingHomo: Bootstrapping Deep Homography With Video Codingcited by 2