mlsanityData to 14 Oct 2026

Soft Expectation and Deep Maximization for Image Feature Detection

arXiv 2104.10291 ↗First posted 21 Apr 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Central to the application of many multi-view geometry algorithms is the extraction of matching points between multiple viewpoints, enabling classical tasks such as camera pose estimation and 3D reconstruction. Many approaches that characterize these points have been proposed based on hand-tuned appearance models or data-driven learning methods. We propose Soft Expectation and Deep Maximization (SEDM), an iterative unsupervised learning process that directly optimizes the repeatability of the features by posing the problem in a similar way to expectation maximization (EM). We found convergence to be reliable and the new model to be more lighting invariant and better at localize the underlying 3D points in a scene, improving SfM quality when compared to other state of the art deep learning detectors.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 21 Apr 2021.

Builds on

29 of 47 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  8. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  10. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  11. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  12. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
17 more
  1. 2020DISK: Learning local features with policy gradientcited by 312
  2. 2016LIFT: Learned Invariant Feature Transformcited by 306
  3. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
  4. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  5. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  6. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  7. 2018LF-Net: Learning Local Features from Imagescited by 151
  8. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
  9. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 118
  10. 2020Robust Image Retrieval-based Visual Localization using Kapturecited by 66
  11. 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
  12. 2019Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Taskcited by 39
  13. 2016Quad-networks: unsupervised learning to rank for interest point detectioncited by 36
  14. 2016Learning Covariant Feature Detectorscited by 25
  15. 2019UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptorcited by 22
  16. 2020UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervisioncited by 17
  17. 2020Visual Localization Using Semantic Segmentation and Depth Predictioncited by 5

Built on by

Not cited yet.