3D Face Reconstruction

73 papers with code • 7 benchmarks • 10 datasets

3D Face Reconstruction is a computer vision task that involves creating a 3D model of a human face from a 2D image or a set of images. The goal of 3D face reconstruction is to reconstruct a digital 3D representation of a person's face, which can be used for various applications such as animation, virtual reality, and biometric identification.

( Image credit: 3DDFA_V2 )

Libraries

Use these libraries to find 3D Face Reconstruction models and implementations

Most implemented papers

Unsupervised Training for 3D Morphable Model Regression

google/tf_mesh_renderer CVPR 2018

We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results.

3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild

XgTu/2DASL-CNN 22 Mar 2019

3D face reconstruction from a single 2D image is a challenging problem with broad applications.

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

soubhiksanyal/RingNet CVPR 2019

The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions.

Learning an Animatable Detailed 3D Face Model from In-The-Wild Images

YadiraF/DECA 7 Dec 2020

Some methods produce faces that cannot be realistically animated because they do not model how wrinkles vary with expression.

Pre-training strategies and datasets for facial representation learning

1adrianb/unsupervised-face-representation 30 Mar 2021

Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e. g. face recognition, facial landmark localization etc.)

HairMapper: Removing Hair From Portraits Using GANs

oneThousand1000/HairMapper CVPR 2022

Removing hair from portrait images is challenging due to the complex occlusions between hair and face, as well as the lack of paired portrait data with/without hair.

Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression

deepinsight/insightface 15 Aug 2022

Even though 3D face reconstruction has achieved impressive progress, most orthogonal projection-based face reconstruction methods can not achieve accurate and consistent reconstruction results when the face is very close to the camera due to the distortion under the perspective projection.

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

billyxyb/facednerf NeurIPS 2023

The ability to create high-quality 3D faces from a single image has become increasingly important with wide applications in video conferencing, AR/VR, and advanced video editing in movie industries.

Multilinear Wavelets: A Statistical Shape Space for Human Faces

TimoBolkart/MultilinearWaveletModel 13 Jan 2014

We show that in comparison to a global multilinear model, our model better preserves fine detail and is computationally faster, while in comparison to a localized PCA model, our model better handles variation in expression, is faster, and allows us to fix identity parameters for a given subject.

A Multiresolution 3D Morphable Face Model and Fitting Framework

patrikhuber/eos 1 Feb 2016

In this paper, we present the Surrey Face Model, a multi-resolution 3D Morphable Model that we make available to the public for non-commercial purposes.