Browse State-of-the-Art › Facial Inpainting

Facial Inpainting

23 papers with code · 3 benchmarks · 5 datasets archive 2025-07-28

Computer VisionMiscellaneousMusic

Facial inpainting (or face completion) is the task of generating plausible facial structures for missing pixels in a face image.

( Image credit: SymmFCNet )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology 3 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): FFHQ (3 judged, 1 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
FFHQ (1 row) DMFN Image Fine-grained Inpainting code — Compare
VggFace2 (1 row) SymmFCNet (Full) Learning Symmetry Consistent Deep CNNs for Face Completion code — Compare
WebFace (1 row) SymmFCNet (Full) Learning Symmetry Consistent Deep CNNs for Face Completion code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 60 · with a code link: 23 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 60 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 60 of 60, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 18 Feb 2019 4 repositories listed
    We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input.
  • 7 Feb 2020 3 repositories listed
    Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.
  • 17 May 2024 2 repositories listed
    Our dataset of masked faces with mask region labels and source code will be available online.
  • 18 Mar 2024 2 repositories listed
    We further improve the StyleGAN output to find the optimal code in the latent space using a new optimization for GAN inversion technique.
  • 23 Oct 2023 2 repositories listed
    Based on this disentanglement, face swapping can be simplified as style and mask swapping.
  • 12 Apr 2023 2 repositories listed
    By using ~40 reference images, PATMAT creates anchor points in MAT's style module, and tunes the model using the fixed anchors to adapt the model to a new face identity.
  • 13 Mar 2023 2 repositories listed
    To introduce strong control for face inpainting, we propose a novel reference-guided face inpainting method that fills the large-scale missing region with identity and texture control guided by a reference face image.
  • 19 Apr 2017 2 repositories listed
    In this paper, we propose an effective face completion algorithm using a deep generative model.
  • 10 Sep 2024 1 repository listed
    Hence, we propose a generative face inpainting method to effectively recover/reconstruct the masked part of a face.
  • 2 Mar 2024 1 repository listed
    The basic framework consists of three components, i. e., IP-Adapter, ControlNet, and Stable Diffusion's inpainting pipeline, for face feature encoding, multi-conditional generation, and face inpainting respectively.
  • 11 Dec 2023 1 repository listed
    We argue that the denoising process is crucially limited by an accumulation of the reconstruction error due to an initial inaccurate reconstruction of the target data.
  • 19 Jan 2023 1 repository listed
    Image inpainting is a technique of completing missing pixels such as occluded region restoration, distracting objects removal, and facial completion.
  • 9 Jan 2023 1 repository listed
    None of the powerful existing models can fill out the missing parts of an image while considering the symmetry and homogeneity of the picture.
  • 17 Nov 2022 1 repository listed
    Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting.
  • 19 Sep 2022 1 repository listed
    Realistic image restoration with high texture areas such as removing face masks is challenging.
  • 20 Feb 2022 1 repository listed
    This paper presents a novel image inpainting framework for face mask removal.
  • 13 Feb 2022 1 repository listed
    We introduce a novel attribute similarity metric to encourage networks to learn the style of facial attributes from the exemplar in a self-supervised way.
  • 26 Nov 2019 1 repository listed
    It is challenging to inpaint face images in the wild, due to the large variation of appearance, such as different poses, expressions and occlusions.
  • 4 Nov 2019 1 repository listed
    Combined variations containing low-resolution and occlusion often present in face images in the wild, e. g., under the scenario of video surveillance.
  • We present Face Swapping GAN (FSGAN) for face swapping and reenactment.
  • 7 Jun 2019 1 repository listed
    Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information.
  • 9 Jan 2019 1 repository listed
    Using this methodology, this paper shows that overfitting is not detectable in the pure GAN models proposed in the literature, in contrast with those using hybrid adversarial losses, which are amongst the most widely…
  • 19 Dec 2018 1 repository listed
    As for missing pixels on both of half-faces, we present a generative reconstruction subnet together with a perceptual symmetry loss to enforce symmetry consistency of recovered structures.
  • Binary Diffusion Probabilistic Model
    23 Jan 2025 0 repositories listed
    We introduce the Binary Diffusion Probabilistic Model (BDPM), a novel generative model optimized for binary data representations.
  • Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation
    19 Sep 2024 0 repositories listed
    Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and…
  • Masked Face Recognition with Generative-to-Discriminative Representations
    27 May 2024 0 repositories listed
    First, we leverage a generative encoder pretrained for face inpainting and finetune it to represent masked faces into category-aware descriptors.
  • Learning Position-Aware Implicit Neural Network for Real-World Face Inpainting
    19 Jan 2024 0 repositories listed
    Face inpainting requires the model to have a precise global understanding of the facial position structure.
  • Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention
    6 Dec 2023 0 repositories listed
    Face inpainting is important in various applications, such as photo restoration, image editing, and virtual reality.
  • DIFAI: Diverse Facial Inpainting using StyleGAN Inversion
    20 Jan 2023 0 repositories listed
    Image inpainting is an old problem in computer vision that restores occluded regions and completes damaged images.
  • Contrastive Learning for Diverse Disentangled Foreground Generation
    4 Nov 2022 0 repositories listed
    We introduce a new method for diverse foreground generation with explicit control over various factors.
  • HiMFR: A Hybrid Masked Face Recognition Through Face Inpainting
    19 Sep 2022 0 repositories listed
  • ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networks
    6 Apr 2022 0 repositories listed
  • Improved Semantic Inpainting Architecture Augmented with a Facial Landmark Detector
    3 Mar 2022 0 repositories listed
  • FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment
    25 Feb 2022 0 repositories listed
  • Contrastive Attention Network with Dense Field Estimation for Face Completion
    20 Dec 2021 0 repositories listed
  • 3DFaceFill: An Analysis-By-Synthesis Approach to Face Completion
    20 Oct 2021 0 repositories listed
  • Deep Face Video Inpainting via UV Mapping
    2 Sep 2021 0 repositories listed
  • FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting
    10 Aug 2021 0 repositories listed
  • FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains
    19 Jun 2021 0 repositories listed
  • Pixel Sampling for Style Preserving Face Pose Editing
    14 Jun 2021 0 repositories listed
  • Extreme Face Inpainting with Sketch-Guided Conditional GAN
    13 May 2021 0 repositories listed
  • Foreground-guided Facial Inpainting with Fidelity Preservation
    7 May 2021 0 repositories listed
  • Learning Oracle Attention for High-fidelity Face Completion
    31 Mar 2020 0 repositories listed
  • Joint Face Completion and Super-resolution using Multi-scale Feature Relation Learning
    29 Feb 2020 0 repositories listed
  • Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting
    5 Feb 2020 0 repositories listed
  • Towards Controllable and Interpretable Face Completion via Structure-Aware and Frequency-Oriented Attentive GANs
    25 Sep 2019 0 repositories listed
  • High Resolution and Fast Face Completion via Progressively Attentive GANs
    1 May 2019 0 repositories listed
  • Cross-spectral Face Completion for NIR-VIS Heterogeneous Face Recognition
    10 Feb 2019 0 repositories listed
  • Face Completion with Semantic Knowledge and Collaborative Adversarial Learning
    8 Dec 2018 0 repositories listed
  • On Hallucinating Context and Background Pixels from a Face Mask using Multi-scale GANs
    17 Nov 2018 0 repositories listed
  • Improved Techniques for GAN based Facial Inpainting
    20 Oct 2018 0 repositories listed
  • Superimposition-guided Facial Reconstruction from Skull
    28 Sep 2018 0 repositories listed
  • Geometry-Aware Face Completion and Editing
    9 Sep 2018 0 repositories listed
  • Identity Preserving Face Completion for Large Ocular Region Occlusion
    23 Jul 2018 0 repositories listed
  • Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart
    23 Mar 2018 0 repositories listed
  • High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks
    23 Jan 2018 0 repositories listed
  • Side Information for Face Completion: a Robust PCA Approach
    20 Jan 2018 0 repositories listed
  • Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
    13 Dec 2017 0 repositories listed
  • r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
    2 Jun 2017 0 repositories listed
  • DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
    16 Nov 2016 0 repositories listed

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections