computer-vision

Facial Inpainting

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in facial-inpainting-2

Trend

Dataset

Best Model

Actions

VggFace2

WebFace

FFHQ

Libraries

i

Use these libraries to find facial-inpainting-2 models and implementations

LonglongaaaGo/EXE-GAN

3 papers 47

Datasets

FFHQ

VGGFace2

CASIA-WebFace

DREAMING Inpainting Dataset

Subtasks

No subtasks available.

Most implemented papers

SC-FEGAN: Face Editing Generative Adversarial Network With User’s Sketch and Color

Jongyoul Park, Youngjoo Jo•Sun Feb 17 2019

This work trained the network with an additional style loss, which made it possible to generate realistic results despite large portions of the image being removed, and is well suited for generating high-quality synthetic images using intuitive user inputs.

320

Content

0

Paper Graph

Image Fine-grained Inpainting

Xinbo Gao, Zheng Hui, Jie Li, Xiumei Wang•Thu Feb 06 2020

A one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields and a novel self-guided regression loss for concentrating on uncertain areas and enhancing the semantic details is presented.

57 0

Paper Graph

Generative Face Completion

Ming-Hsuan Yang, Jimei Yang, Yijun Li, Sifei Liu•Tue Apr 18 2017

This paper demonstrates qualitatively and quantitatively that the proposed effective face completion algorithm is able to deal with a large area of missing pixels in arbitrary shapes and generate realistic face completion results.

624 0

Paper Graph

Reference-Guided Large-Scale Face Inpainting With Identity and Texture Control

Wuyang Luo, Su Yang, Weishan Zhang•Sun Mar 12 2023

This work proposes a dual control one-stage framework that decouples the reference image into two levels for flexible control: High-level identity information and low-level texture information, where the identity information figures out the shape of the face and the texture information depicts the component-aware texture.

17 0

Paper Graph

PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face inpainting

F. D. L. Torre, Saman Motamed, Jianjin Xu, Chenhuan Wu•Tue Apr 11 2023

It is demonstrated that PATMAT outperforms state-of-the-art models in terms of image quality, the preservation of person-specific details, and the identity of the subject, and the results suggest that PATMAT can be a promising approach for improving the quality of personalized face inpainting 2.

4 0

Paper Graph

E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion

Maomao Li, Genlan Yuan, Cairong Wang, Zhian Liu, Yong Zhang, Yongwei Nie, Jue Wang, Dong Xu•Sun Oct 22 2023

This paper proposes a novel approach to face swapping from the perspective of fine-grained facial editing, dubbed "editing for swapping"(E4S), which outperforms existing methods in preserving texture, shape, and lighting.

9 0

Paper Graph

Learning Symmetry Consistent Deep CNNs for Face Completion

W. Zuo, Lei Zhang, M. Wang, Xiaoming Li, Ming Liu, Jieru Zhu, Guosheng Hu•Tue Dec 18 2018

Two kinds of symmetry-enforcing modules are Leveraged to form a symmetry-consistent CNN model (i.e., SymmFCNet) for effective face completion and can generate globally consistent results on images with synthetic and real occlusions, and performs favorably against state-of-the-arts.

27 0

Paper Graph

Detecting Overfitting of Deep Generative Networks via Latent Recovery

J. Rabin, Ryan Webster, Loïc Simon, F. Jurie•Tue Jan 08 2019

This work shows how simple losses are highly effective at reconstructing images for deep generators and analyzing the statistics of reconstruction errors for training versus validation images shows that pure GAN models appear to generalize well, in contrast with those using hybrid adversarial losses, which are amongst the most widely applied generative methods.

105 0

Paper Graph

Does Generative Face Completion Help Face Recognition?

I. Masi, Wael AbdAlmageed, Joe Mathai•Fri May 31 2019

This work offers a face completion encoder-decoder, based on a convolutional operator with a gating mechanism, trained with an ample set of face occlusions, and proposes to play the occlusion game: the authors render 3D objects onto different face parts, providing precious knowledge of what the impact is of effectively removing those occLusions.

28 0

Paper Graph

FSGAN: Subject Agnostic Face Swapping and Reenactment

Tal Hassner, Y. Nirkin, Y. Keller•Thu Aug 15 2019

A novel recurrent neural network (RNN)-based approach for face reenactment which adjusts for both pose and expression variations and can be applied to a single image or a video sequence and uses a novel Poisson blending loss which combines Poisson optimization with perceptual loss.

685 0

Paper Graph

Adding a benchmark result helps the community track progress.