|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM286368404 |
| 003 |
DE-627 |
| 005 |
20250223192148.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2019 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2018.2837742
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n0954.xml
|
| 035 |
|
|
|a (DE-627)NLM286368404
|
| 035 |
|
|
|a (NLM)29994297
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Yudong Guo
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a CNN-Based Real-Time Dense Face Reconstruction with Inverse-Rendered Photo-Realistic Face Images
|
| 264 |
|
1 |
|c 2019
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 20.11.2019
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a 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
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Juyong Zhang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jianfei Cai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Boyi Jiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jianmin Zheng
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 41(2019), 6 vom: 26. Juni, Seite 1294-1307
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:41
|g year:2019
|g number:6
|g day:26
|g month:06
|g pages:1294-1307
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2018.2837742
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 41
|j 2019
|e 6
|b 26
|c 06
|h 1294-1307
|