Facial Inpainting

21 papers with code • 3 benchmarks • 4 datasets

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

( Image credit: SymmFCNet )

Libraries

Use these libraries to find Facial Inpainting models and implementations

Latest papers with no code

Face Swap via Diffusion Model

no code yet • 2 Mar 2024

This technical report presents a diffusion model based framework for face swapping between two portrait images.

Learning Position-Aware Implicit Neural Network for Real-World Face Inpainting

no code yet • 19 Jan 2024

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

no code yet • 6 Dec 2023

Specifically, we insert parallel attention matrices to each cross-attention module in the denoising network, which attends to features extracted from reference images by an identity encoder.

DIFAI: Diverse Facial Inpainting using StyleGAN Inversion

no code yet • 20 Jan 2023

Image inpainting is an old problem in computer vision that restores occluded regions and completes damaged images.

Contrastive Learning for Diverse Disentangled Foreground Generation

no code yet • 4 Nov 2022

We introduce a new method for diverse foreground generation with explicit control over various factors.

ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networks

no code yet • 6 Apr 2022

Furthermore, to better improve the inter-coordination between the corrupted and non-corrupted regions and enhance the intra-coordination in corrupted regions, we design InCo2 Loss, a pair of similarity based losses to constrain the feature consistency.

FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

no code yet • 25 Feb 2022

Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training on those faces.

Contrastive Attention Network with Dense Field Estimation for Face Completion

no code yet • 20 Dec 2021

This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images.

3DFaceFill: An Analysis-By-Synthesis Approach to Face Completion

no code yet • 20 Oct 2021

Existing face completion solutions are primarily driven by end-to-end models that directly generate 2D completions of 2D masked faces.

Deep Face Video Inpainting via UV Mapping

no code yet • 2 Sep 2021

In Stage I, we perform face inpainting in the UV space.