mlsanityData to 7 Oct 2026

LIFE: Lighting Invariant Flow Estimation

arXiv 2104.03097 ↗First posted 7 Apr 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small displacement and constant illuminations, but cannot work well on cases with large viewpoint change and lighting variations because of the lack of pixel-wise flow annotations for such cases. We observe that via the Structure-from-Motion (SfM) techniques, one can easily estimate relative camera poses between image pairs with large viewpoint change and lighting variations. We propose a novel weakly supervised framework LIFE to train a neural network for estimating accurate lighting-invariant flows between image pairs. Sparse correspondences are conventionally established via feature matching with descriptors encoding local image contents. However, local image contents are inevitably ambiguous and error-prone during the cross-image feature matching process, which hinders downstream tasks. We propose to guide feature matching with the flows predicted by LIFE, which addresses the ambiguous matching by utilizing abundant context information in the image pairs. We show that LIFE outperforms previous flow learning frameworks by large margins in challenging scenarios, consistently improves feature matching, and benefits downstream tasks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 39 of its 63 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

39 of 63 references.

References · 39

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  4. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  5. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  6. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  7. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  8. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  9. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  10. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  11. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  12. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
27 more
  1. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  2. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  3. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  4. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  5. 2018Neighbourhood Consensus Networkscited by 173
  6. 2018LF-Net: Learning Local Features from Imagescited by 151
  7. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  8. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  9. 2017Convolutional neural network architecture for geometric matchingcited by 138
  10. 2020What Matters in Unsupervised Optical Flowcited by 124
  11. 2020Epipolar Transformerscited by 117
  12. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  13. 2016Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothnesscited by 101
  14. 2018Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimationcited by 94
  15. 2019A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularizationcited by 76
  16. 2018DGC-Net: Dense Geometric Correspondence Networkcited by 67
  17. 2019DDFlow: Learning Optical Flow with Unlabeled Data Distillationcited by 63
  18. 2019Content-Aware Unsupervised Deep Homography Estimationcited by 62
  19. 2020Deep Homography Estimation for Dynamic Scenescited by 60
  20. 2020GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Networkcited by 53
  21. 2020RANSAC-Flow: generic two-stage image alignmentcited by 48
  22. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47
  23. 2020Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matchingcited by 36
  24. 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
  25. 2019A Cross-Season Correspondence Dataset for Robust Semantic Segmentationcited by 28
  26. 2018Online Temporal Calibration for Monocular Visual-Inertial Systemscited by 26
  27. 2020Optical Flow in Dense Foggy Scenes using Semi-Supervised Learningcited by 20

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2.

6 papers.

  1. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  2. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  3. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  4. 2023PMatch: Paired Masked Image Modeling for Dense Geometric Matchingcited by 29
  5. 2023FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flowcited by 3
  6. 2022A qualitative investigation of optical flow algorithms for video denoisingcited by 0