mlsanityData to 14 Oct 2026

Inverse Compositional Spatial Transformer Networks

arXiv 1612.03897 ↗First posted 12 Dec 2016cs.CV cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

In this paper, we establish a theoretical connection between the classical Lucas & Kanade (LK) algorithm and the emerging topic of Spatial Transformer Networks (STNs). STNs are of interest to the vision and learning communities due to their natural ability to combine alignment and classification within the same theoretical framework. Inspired by the Inverse Compositional (IC) variant of the LK algorithm, we present Inverse Compositional Spatial Transformer Networks (IC-STNs). We demonstrate that IC-STNs can achieve better performance than conventional STNs with less model capacity; in particular, we show superior performance in pure image alignment tasks as well as joint alignment/classification problems on real-world problems.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 4; 2023: 7; 2024: 3; 2025: 6.

29 papers.

Sort:

  1. 2023DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Videocited by 74
  2. 2021GAN-Supervised Dense Visual Alignmentcited by 62
  3. 2021Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classificationcited by 31
  4. 2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
  5. 2021Deep Feedback Inverse Problem Solvercited by 11
  6. 2023Canonical Factors for Hybrid Neural Fieldscited by 8
  7. 2021Learning Canonical 3D Object Representation for Fine-Grained Recognitioncited by 7
  8. 2022HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Trackingcited by 7
  9. 2022Learning to See Through with Eventscited by 7
  10. 2024Tilt your Head: Activating the Hidden Spatial-Invariance of Classifierscited by 7
  11. 2024SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Imagescited by 6
  12. 2021Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapescited by 4
17 more
  1. 2021CNN-based Ego-Motion Estimation for Fast MAV Maneuverscited by 3
  2. 2023High-Quality 3D Face Reconstruction with Affine Convolutional Networkscited by 3
  3. 2024Metric Convolutions: A Unifying Theory to Adaptive Image Convolutionscited by 3
  4. 2025Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averagingcited by 3
  5. 2025Geometrically Constrained and Token-Based Probabilistic Spatial Transformerscited by 3
  6. 2021The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutionscited by 2
  7. 2022Spatial Transformation for Image Composition via Correspondence Learningcited by 2
  8. 2023TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimationcited by 2
  9. 2025Saccadic Vision for Fine-Grained Visual Classificationcited by 2
  10. 2021Human Pose Transfer with Augmented Disentangled Feature Consistencycited by 1
  11. 2022Perspective Transformation Layercited by 1
  12. 2023Spatial-Temporal Alignment Network for Action Recognitioncited by 1
  13. 2023GeoDeformer: Geometric Deformable Transformer for Action Recognitioncited by 1
  14. 2025Adaptive Low Light Enhancement via Joint Global-Local Illumination Adjustmentcited by 1
  15. 2025Robust Canonicalization through Bootstrapped Data Re-Alignmentcited by 1
  16. 2025FastJAM: a Fast Joint Alignment Model for Imagescited by 1
  17. 2023Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifoldcited by 0