mlsanityData to 14 Oct 2026

Extracting Deformation-Aware Local Features by Learning to Deform

arXiv 2111.10617 ↗First posted 20 Nov 2021cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Despite the advances in extracting local features achieved by handcrafted and learning-based descriptors, they are still limited by the lack of invariance to non-rigid transformations. In this paper, we present a new approach to compute features from still images that are robust to non-rigid deformations to circumvent the problem of matching deformable surfaces and objects. Our deformation-aware local descriptor, named DEAL, leverages a polar sampling and a spatial transformer warping to provide invariance to rotation, scale, and image deformations. We train the model architecture end-to-end by applying isometric non-rigid deformations to objects in a simulated environment as guidance to provide highly discriminative local features. The experiments show that our method outperforms state-of-the-art handcrafted, learning-based image, and RGB-D descriptors in different datasets with both real and realistic synthetic deformable objects in still images. The source code and trained model of the descriptor are publicly available at https://www.verlab.dcc.ufmg.br/descriptors/neurips2021.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 20 Nov 2021.

Builds on

24 of 52 references.

References · 24

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  3. 2017Deformable Convolutional Networkscited by 1,488
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  5. 2015Spatial Transformer Networkscited by 1,429
  6. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  7. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  8. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  9. 2016LIFT: Learned Invariant Feature Transformcited by 306
  10. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
  11. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  12. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
12 more
  1. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  2. 2018LF-Net: Learning Local Features from Imagescited by 151
  3. 2017Convolutional neural network architecture for geometric matchingcited by 138
  4. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  5. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
  6. 2019DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Datacited by 77
  7. 2017End-to-end weakly-supervised semantic alignmentcited by 60
  8. 2018GeoDesc: Learning Local Descriptors by Integrating Geometry Constraintscited by 52
  9. 2018Detect-to-Retrieve: Efficient Regional Aggregation for Image Searchcited by 39
  10. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  11. 2018Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspectivecited by 19
  12. 2018Geometry-Aware Network for Non-Rigid Shape Prediction from a Single Viewcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 0; 2026: 1.

7 papers.

  1. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  2. 2023Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypointscited by 11
  3. 2023The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenescited by 5
  4. 2024Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondencecited by 5
  5. 2022Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Imagescited by 2
  6. 2023Improving the matching of deformable objects by learning to detect keypointscited by 1
  7. 2026IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1cited by 0