mlsanityData to 7 Oct 2026

Perspective Transformation Layer

arXiv 2201.05706 ↗First posted 14 Jan 2022cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Incorporating geometric transformations that reflect the relative position changes between an observer and an object into computer vision and deep learning models has attracted much attention in recent years. However, the existing proposals mainly focus on the affine transformation that is insufficient to reflect such geometric position changes. Furthermore, current solutions often apply a neural network module to learn a single transformation matrix, which not only ignores the importance of multi-view analysis but also includes extra training parameters from the module apart from the transformation matrix parameters that increase the model complexity. In this paper, a perspective transformation layer is proposed in the context of deep learning. The proposed layer can learn homography, therefore reflecting the geometric positions between observers and objects. In addition, by directly training its transformation matrices, a single proposed layer can learn an adjustable number of multiple viewpoints without considering module parameters. The experiments and evaluations confirm the superiority of the proposed layer.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 14 Jan 2022.

Builds on

19 of 45 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2015Spatial Transformer Networkscited by 1,423
  6. 2016Group Equivariant Convolutional Networkscited by 1,154
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  8. 2017Dynamic Routing Between Capsulescited by 689
  9. 2017Exploring Generalization in Deep Learningcited by 595
  10. 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 187
  11. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  12. 2017Polar Transformer Networkscited by 81
7 more
  1. 2018Deep attention-based classification network for robust depth predictioncited by 36
  2. 2019Equivariant Transformer Networkscited by 35
  3. 2016Inverse Compositional Spatial Transformer Networkscited by 29
  4. 2017On Classification of Distorted Images with Deep Convolutional Neural Networkscited by 26
  5. 2021DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoderscited by 23
  6. 2016gvnn: Neural Network Library for Geometric Computer Visioncited by 4
  7. 2020Detecting Lane and Road Markings at A Distance with Perspective Transformer Layerscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarkingcited by 0