mlsanityData to 14 Oct 2026

Improved Detection of Face Presentation Attacks Using Image Decomposition

arXiv 2103.12201 ↗First posted 22 Mar 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Presentation attack detection (PAD) is a critical component in secure face authentication. We present a PAD algorithm to distinguish face spoofs generated by a photograph of a subject from live images. Our method uses an image decomposition network to extract albedo and normal. The domain gap between the real and spoof face images leads to easily identifiable differences, especially between the recovered albedo maps. We enhance this domain gap by retraining existing methods using supervised contrastive loss. We present empirical and theoretical analysis that demonstrates that contrast and lighting effects can play a significant role in PAD; these show up, particularly in the recovered albedo. Finally, we demonstrate that by combining all of these methods we achieve state-of-the-art results on both intra-dataset testing for CelebA-Spoof, OULU, CASIA-SURF datasets and inter-dataset setting on SiW, CASIA-MFSD, Replay-Attack and MSU-MFSD datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 61 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

36 of 61 references.

References · 36

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  5. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  6. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 632
  7. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  8. 2020Domain Generalization using Causal Matchingcited by 225
  9. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  10. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  11. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  12. 2018Nonlinear 3D Face Morphable Modelcited by 157
24 more
  1. 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
  2. 2017SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wildcited by 110
  3. 2019Generalizing to unseen domains via distribution matchingcited by 110
  4. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  5. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  6. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 105
  7. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 100
  8. 2015face anti-spoofing based on color texture analysiscited by 82
  9. 2019Deep Pixel-wise Binary Supervision for Face Presentation Attack Detectioncited by 76
  10. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  11. 2017Neural Face Editing with Intrinsic Image Disentanglingcited by 70
  12. 2020Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofingcited by 70
  13. 2020Face Anti-Spoofing Via Disentangled Representation Learningcited by 65
  14. 2019CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofingcited by 61
  15. 2018Face De-Spoofing: Anti-Spoofing via Noise Modelingcited by 60
  16. 2020Towards Recognizing Unseen Categories in Unseen Domainscited by 56
  17. 2020Face Forgery Detection by 3D Decompositioncited by 53
  18. 2019Learning Meta Model for Zero- and Few-shot Face Anti-spoofingcited by 44
  19. 2020Multi-Modal Face Anti-Spoofing Based on Central Difference Networkscited by 36
  20. 20193D Face Modeling From Diverse Raw Scan Datacited by 25
  21. 2020SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimationcited by 25
  22. 2016Production-Level Facial Performance Capture Using Deep Convolutional Neural Networkscited by 14
  23. 2020Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofingcited by 14
  24. 2018Exploiting temporal and depth information for multi-frame face anti-spoofingcited by 10

Built on by

Not cited yet.