computer-vision-7

Face Model

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in face-model-7

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find face-model-7 models and implementations

unibas-gravis/parametric-face-image…

3 papers 232

Datasets

Procedural Human Action Videos

Subtasks

No subtasks available.

Most implemented papers

Learning a model of facial shape and expression from 4D scans

Michael J. Black, J. Romero, Timo Bolkart, Tianye Li, Hao Li•Sun Nov 19 2017

Faces Learned with an Articulated Model and Expressions is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model and is compared to these models by fitting them to static 3D scans and 4D sequences using the same optimization method.

1490

Content

0

Paper Graph

Face Detection with End-to-End Integration of a ConvNet and a 3D Model

Tianfu Wu, Yizhou Wang, Yunzhu Li, Benyuan Sun•Wed Jun 01 2016

This paper presents a method for face detection in the wild, which integrates a ConvNet and a 3D mean face model in an end-to-end multi-task discriminative learning framework and addresses two issues in adapting state-of-the-art generic object detection ConvNets.

131 0

Paper Graph

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Yanfeng Wang, Yao Feng, Fan Wu, Xiaohu Shao, Xi Zhou•Tue Mar 20 2018

A straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment and surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin.

723 0

Paper Graph

SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness

Naser Damer, Arjan Kuijper, P. Terhorst, J. Kolf, Florian Kirchbuchner•Thu Mar 19 2020

This work proposes a novel concept to measure face quality based on an arbitrary face recognition model that avoids the training phase completely and further outperforms all baseline approaches by a large margin.

198 0

Paper Graph

Morphable Face Models - An Open Framework

B. Egger, Thomas Gerig, Andreas Forster, Clemens Blumer, M. Lüthi, Sandro Schönborn, T. Vetter•Sun Sep 24 2017

A novel open-source pipeline for face registration based on Gaussian processes as well as an application to face image analysis and a new version of the Basel Face Model with improved age distribution and an additional facial expression model are presented.

294 0

Paper Graph

Training Deep Face Recognition Systems with Synthetic Data

B. Egger, Thomas Gerig, T. Vetter, Adam Kortylewski, Andreas Schneider, Andreas Morel-Forster•Thu Feb 15 2018

This work explores how synthetically generated data can be used to decrease the number of real-world images needed for training deep face recognition systems, and makes use of a 3D morphable face model for the generation of images with arbitrary amounts of facial identities and with full control over image variations.

56 0

Paper Graph

Face Alignment in Full Pose Range: A 3D Total Solution

Xiaoming Liu, Zhen Lei, S. Li, Xiangyu Zhu, Hailin Shi•Sun Nov 22 2015

3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks, is proposed, which utilizes 3D information to synthesize face images in profile views to provide abundant samples for training.

778 0

Paper Graph

Generating 3D faces using Convolutional Mesh Autoencoders

Michael J. Black, Soubhik Sanyal, Timo Bolkart, Anurag Ranjan•Wed Jul 25 2018

This work introduces a versatile model that learns a non-linear representation of a face using spectral convolutions on a mesh surface and shows that, replacing the expression space of an existing state-of-the-art face model with this model, achieves a lower reconstruction error.

612 0

Paper Graph

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

Jiashi Feng, Jian Zhao, Zihang Jiang, X. Tu, Yao Luo, M. Xie, Yang Zhao, L. He, Zheng Ma•Thu Mar 21 2019

3D face reconstruction from a single image is an important task in many multimedia applications. Recent works typically learn a CNN-based 3D face model that regresses coefficients of a 3D Morphable Model (3DMM) from 2D images to perform 3D face reconstruction. However, the shortage of training data with 3D annotations considerably limits performance of these methods. To alleviate this issue, we propose a novel 2D-Assisted Learning (2DAL) method that can effectively use “in the wild” 2D face images with noisy landmark information to substantially improve 3D face model learning. Specifically, taking the sparse 2D facial landmark heatmaps as additional information, 2DAL introduces four novel self-supervision schemes that view the 2D landmark and 3D landmark prediction as a self-mapping process, including the landmark self-prediction consistency for 2D and 3D faces respectively, cycle-consistency over the 2D landmark prediction and self-critic over the predicted 3DMM coefficients based on landmark prediction. Using these four self-supervision schemes, 2DAL significantly relieves the demands for the the conventional paired 2D-to-3D annotations and gives much higher-quality 3D face models without requiring any additional 3D annotations. Experiments on AFLW2000-3D, AFLW-LFPA and Florence benchmarks show that our method outperforms state-of-the-arts for both 3D face reconstruction and dense face alignment by a large margin.

99 0

Paper Graph

CONFIG: Controllable Neural Face Image Generation

J. Shotton, T. Baltrušaitis, Stephan J. Garbin, Marek Kowalski, V. Estellers, Matthew Johnson•Tue May 05 2020

This work proposes ConfigNet, a neural face model that allows for controlling individual aspects of output images in semantically meaningful ways and that is a significant step on the path towards finely-controllable neural rendering.

98 0

Paper Graph

Adding a benchmark result helps the community track progress.