mlsanityData to 14 Oct 2026

Generative Face Completion

arXiv 1704.05838 ↗First posted 19 Apr 2017cs.CVcited by 79

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose an effective face completion algorithm using a deep generative model. Different from well-studied background completion, the face completion task is more challenging as it often requires to generate semantically new pixels for the missing key components (e.g., eyes and mouths) that contain large appearance variations. Unlike existing nonparametric algorithms that search for patches to synthesize, our algorithm directly generates contents for missing regions based on a neural network. The model is trained with a combination of a reconstruction loss, two adversarial losses and a semantic parsing loss, which ensures pixel faithfulness and local-global contents consistency. With extensive experimental results, we demonstrate qualitatively and quantitatively that our model is able to deal with a large area of missing pixels in arbitrary shapes and generate realistic face completion results.

Key facts. Cited by 79 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 32; 2022: 21; 2023: 13; 2024: 9; 2025: 3; 2026: 1.

79 papers.

Sort:

By area:

  1. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  2. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 169
  3. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  4. 2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
  5. 2022Synthesizing Informative Training Samples with GANcited by 77
  6. 2022Synthetic Data -- what, why and how?cited by 67
  7. 2023Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancementcited by 57
  8. 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
  9. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  10. 2022NeRF-In: Free-Form NeRF Inpainting with RGB-D Priorscited by 43
  11. 2023Relightify: Relightable 3D Faces from a Single Image via Diffusion Modelscited by 34
  12. 2021DeFLOCNet: Deep Image Editing via Flexible Low-level Controlscited by 26
38 more
  1. 2021BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learningcited by 26
  2. 2021RoI Tanh-polar Transformer Network for Face Parsing in the Wildcited by 23
  3. 2021Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semanticscited by 20
  4. 2021AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsingcited by 16
  5. 2024FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Featurescited by 14
  6. 2021Vision-based Neural Scene Representations for Spacecraftcited by 12
  7. 2023RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detectioncited by 12
  8. 2023AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detectioncited by 12
  9. 2021Biometrics in the Era of COVID-19: Challenges and Opportunitiescited by 11
  10. 2021FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpaintingcited by 11
  11. 2022Generative Adversarial Networks for Image Super-Resolution: A Surveycited by 11
  12. 2023Reference-Guided Large-Scale Face Inpainting with Identity and Texture Controlcited by 10
  13. 2021Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Trackingcited by 9
  14. 2022Enhancement of Novel View Synthesis Using Omnidirectional Image Completioncited by 9
  15. 2023Parameter Efficient Local Implicit Image Function Network for Face Segmentationcited by 8
  16. 2021Temporally coherent video anonymization through GAN inpaintingcited by 7
  17. 2021Deep Face Video Inpainting via UV Mappingcited by 7
  18. 2021Generative Memory-Guided Semantic Reasoning Model for Image Inpaintingcited by 7
  19. 2021Segmentation-Reconstruction-Guided Facial Image De-occlusioncited by 6
  20. 2021Depth as Attention for Face Representation Learningcited by 5
  21. 2021Locality-aware Channel-wise Dropout for Occluded Face Recognitioncited by 5
  22. 2021GANmapper: geographical data translationcited by 5
  23. 2022A Deep Learning Framework to Reconstruct Face under Maskcited by 5
  24. 2022High-Quality Pluralistic Image Completion via Code Shared VQGANcited by 5
  25. 2023FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restorationcited by 5
  26. 2021DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Trainingcited by 4
  27. 2021JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolutioncited by 4
  28. 2021In-N-Out: Towards Good Initialization for Inpainting and Outpaintingcited by 4
  29. 2021Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnailscited by 4
  30. 2021MisConv: Convolutional Neural Networks for Missing Datacited by 4
  31. 2021Fully Context-Aware Image Inpainting with a Learned Semantic Pyramidcited by 4
  32. 2022ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networkscited by 3
  33. 2022FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusioncited by 3
  34. 2022A Survey on Computer Vision based Human Analysis in the COVID-19 Eracited by 3
  35. 2023Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Predictioncited by 3
  36. 20213DFaceFill: An Analysis-By-Synthesis Approach to Face Completioncited by 2
  37. 2022Face Beneath the Ink: Synthetic Data and Tattoo Removal with Application to Face Recognitioncited by 2
  38. 2022Multi-feature Co-learning for Image Inpaintingcited by 2

50 most cited of 79 All 79 (JSON)