mlsanityData to 7 Oct 2026

Controllable Data Augmentation Through Deep Relighting

arXiv 2110.13996 ↗First posted 26 Oct 2021cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

At the heart of the success of deep learning is the quality of the data. Through data augmentation, one can train models with better generalization capabilities and thus achieve greater results in their field of interest. In this work, we explore how to augment a varied set of image datasets through relighting so as to improve the ability of existing models to be invariant to illumination changes, namely for learned descriptors. We develop a tool, based on an encoder-decoder network, that is able to quickly generate multiple variations of the illumination of various input scenes whilst also allowing the user to define parameters such as the angle of incidence and intensity. We demonstrate that by training models on datasets that have been augmented with our pipeline, it is possible to achieve higher performance on localization benchmarks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 57 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

45 of 57 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  8. 2017Random Erasing Data Augmentationcited by 1,235
  9. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  10. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  12. 2018Albumentations: fast and flexible image augmentationscited by 558
33 more
  1. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  2. 2015A Neural Algorithm of Artistic Stylecited by 480
  3. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  4. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  5. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  6. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 219
  7. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  8. 2019Single Image Portrait Relightingcited by 152
  9. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  10. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  11. 2018A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspectivecited by 111
  12. 2019Learning Physics-guided Face Relighting under Directional Lightcited by 90
  13. 2020The Hessian Penalty: A Weak Prior for Unsupervised Disentanglementcited by 90
  14. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  15. 2020Guided Variational Autoencoder for Disentanglement Learningcited by 57
  16. 2020A Disentangling Invertible Interpretation Network for Explaining Latent Representationscited by 57
  17. 2017Smart Augmentation - Learning an Optimal Data Augmentation Strategycited by 54
  18. 2018Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoderscited by 49
  19. 2021Self-supervised Outdoor Scene Relightingcited by 48
  20. 2021Towards High Fidelity Face Relighting with Realistic Shadowscited by 42
  21. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  22. 2020Disentangled Image Generation Through Structured Noise Injectioncited by 39
  23. 2017Improving Deep Learning using Generic Data Augmentationcited by 36
  24. 2020Learning to Factorize and Relight a Citycited by 36
  25. 2019A Neural Rendering Framework for Free-Viewpoint Relightingcited by 26
  26. 2020VIDIT: Virtual Image Dataset for Illumination Transfercited by 26
  27. 2019STaDA: Style Transfer as Data Augmentationcited by 21
  28. 2020Learning Disentangled Representations with Latent Variation Predictabilitycited by 19
  29. 2017Disentangling Factors of Variation by Mixing Themcited by 18
  30. 2020AIM 2020: Scene Relighting and Illumination Estimation Challengecited by 18
  31. 2020Image Stylization for Robust Featurescited by 11
  32. 2019Disentangling and Learning Robust Representations with Natural Clusteringcited by 10
  33. 2019Learning Disentangled Representations via Independent Subspacescited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 1.

4 papers.

  1. 2022VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relightingcited by 37
  2. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  3. 2023Controllable Light Diffusion for Portraitscited by 11
  4. 2021SIRfyN: Single Image Relighting from your Neighborscited by 1