CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images
With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images. The success of CNN-based methods relies on a large number of labeled data. The state-of-the-art synthesizes su...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/141937 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-141937 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1419372020-08-06T02:44:45Z CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images Guo, Yudong Zhang, Juyong Cai, Jianfei Jiang, Boyi Zheng, Jianmin School of Computer Science and Engineering Engineering::Computer science and engineering 3D Face Reconstruction Face Tracking With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images. The success of CNN-based methods relies on a large number of labeled data. The state-of-the-art synthesizes such data using a coarse morphable face model, which however has difficulty to generate detailed photo-realistic images of faces (with wrinkles). This paper presents a novel face data generation method. Specifically, we render a large number of photo-realistic face images with different attributes based on inverse rendering. Furthermore, we construct a fine-detailed face image dataset by transferring different scales of details from one image to another. We also construct a large number of video-type adjacent frame pairs by simulating the distribution of real video data.11.All these coarse-scale and fine-scale photo-realistic face image datasets can be downloaded from https://github.com/Juyong/3DFace. With these nicely constructed datasets, we propose a coarse-to-fine learning framework consisting of three convolutional networks. The networks are trained for real-time detailed 3D face reconstruction from monocular video as well as from a single image. Extensive experimental results demonstrate that our framework can produce high-quality reconstruction but with much less computation time compared to the state-of-the-art. Moreover, our method is robust to pose, expression and lighting due to the diversity of data. Accepted version We thank Thomas Vetter et al. and Kun Zhou et al. forallowing us to use their 3D face datasets. This work wassupported by the National Key R&D Program of China(No. 2016YFC0800501), the National Natural Science Foun-dation of China (No. 61672481), and the Youth InnovationPromotion Association of CAS. The research is also partiallysupported by a grant (M4082186) for Joint WASP/NTU andMOE Tier-2 Grant (2016-T2-2-065). 2020-06-12T02:02:23Z 2020-06-12T02:02:23Z 2019 Journal Article Guo, Y., Zhang, J., Cai, J., Jiang, B., & Zheng, J. (2019). CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images. IEEE transactions on pattern analysis and machine intelligence, 41(6), 1294-1307. doi:10.1109/TPAMI.2018.2837742 0162-8828 https://hdl.handle.net/10356/141937 10.1109/TPAMI.2018.2837742 29994297 2-s2.0-85047013656 6 41 1294 1307 en IEEE transactions on pattern analysis and machine intelligence © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/ 10.1109/TPAMI.2018.2837742 application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering 3D Face Reconstruction Face Tracking |
spellingShingle |
Engineering::Computer science and engineering 3D Face Reconstruction Face Tracking Guo, Yudong Zhang, Juyong Cai, Jianfei Jiang, Boyi Zheng, Jianmin CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
description |
With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images. The success of CNN-based methods relies on a large number of labeled data. The state-of-the-art synthesizes such data using a coarse morphable face model, which however has difficulty to generate detailed photo-realistic images of faces (with wrinkles). This paper presents a novel face data generation method. Specifically, we render a large number of photo-realistic face images with different attributes based on inverse rendering. Furthermore, we construct a fine-detailed face image dataset by transferring different scales of details from one image to another. We also construct a large number of video-type adjacent frame pairs by simulating the distribution of real video data.11.All these coarse-scale and fine-scale photo-realistic face image datasets can be downloaded from https://github.com/Juyong/3DFace. With these nicely constructed datasets, we propose a coarse-to-fine learning framework consisting of three convolutional networks. The networks are trained for real-time detailed 3D face reconstruction from monocular video as well as from a single image. Extensive experimental results demonstrate that our framework can produce high-quality reconstruction but with much less computation time compared to the state-of-the-art. Moreover, our method is robust to pose, expression and lighting due to the diversity of data. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Guo, Yudong Zhang, Juyong Cai, Jianfei Jiang, Boyi Zheng, Jianmin |
format |
Article |
author |
Guo, Yudong Zhang, Juyong Cai, Jianfei Jiang, Boyi Zheng, Jianmin |
author_sort |
Guo, Yudong |
title |
CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
title_short |
CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
title_full |
CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
title_fullStr |
CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
title_full_unstemmed |
CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
title_sort |
cnn-based real-time dense face reconstruction with inverse-rendered photo-realistic face images |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/141937 |
_version_ |
1681056770487746560 |