Disentangled Lifespan Face Synthesis
Uložené v:
| Názov: | Disentangled Lifespan Face Synthesis |
|---|---|
| Autori: | He, Sen, Liao, Wentong, Yang, Michael Ying, Song, Yi-zhe, Rosenhahn, Bodo, Xiang, Tao |
| Zdroj: | 2021 IEEE/CVF International Conference on Computer Vision (ICCV). :3857-3866 |
| Publication Status: | Preprint |
| Informácie o vydavateľovi: | IEEE, 2021. |
| Rok vydania: | 2021 |
| Predmety: | FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 22/1 OA procedure, 02 engineering and technology |
| Popis: | A lifespan face synthesis (LFS) model aims to generate a set of photo-realistic face images of a person's whole life, given only one snapshot as reference. The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture, while being identity preserving. This is extremely challenging because the shape and texture characteristics of a face undergo separate and highly nonlinear transformations w.r.t. age. Most recent LFS models are based on generative adversarial networks (GANs) whereby age code conditional transformations are applied to a latent face representation. They benefit greatly from the recent advancements of GANs. However, without explicitly disentangling their latent representations into the texture, shape and identity factors, they are fundamentally limited in modeling the nonlinear age-related transformation on texture and shape whilst preserving identity. In this work, a novel LFS model is proposed to disentangle the key face characteristics including shape, texture and identity so that the unique shape and texture age transformations can be modeled effectively. This is achieved by extracting shape, texture and identity features separately from an encoder. Critically, two transformation modules, one conditional convolution based and the other channel attention based, are designed for modeling the nonlinear shape and texture feature transformations respectively. This is to accommodate their rather distinct aging processes and ensure that our synthesized images are both age-sensitive and identity preserving. Extensive experiments show that our LFS model is clearly superior to the state-of-the-art alternatives. Codes and demo are available on our project website: \url{https://senhe.github.io/projects/iccv_2021_lifespan_face}. To appear in ICCV 2021 |
| Druh dokumentu: | Article Conference object |
| DOI: | 10.1109/iccv48922.2021.00385 |
| DOI: | 10.48550/arxiv.2108.02874 |
| Prístupová URL adresa: | http://arxiv.org/pdf/2108.02874 http://arxiv.org/abs/2108.02874 https://research.utwente.nl/en/publications/e9e2cd3d-3b2b-426f-9551-b1364bb1065e https://doi.org/10.1109/ICCV48922.2021.00385 |
| Rights: | STM Policy #29 CC BY |
| Prístupové číslo: | edsair.doi.dedup.....99e3e3ad656dec775d21fd6fe1dcf109 |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | A lifespan face synthesis (LFS) model aims to generate a set of photo-realistic face images of a person's whole life, given only one snapshot as reference. The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture, while being identity preserving. This is extremely challenging because the shape and texture characteristics of a face undergo separate and highly nonlinear transformations w.r.t. age. Most recent LFS models are based on generative adversarial networks (GANs) whereby age code conditional transformations are applied to a latent face representation. They benefit greatly from the recent advancements of GANs. However, without explicitly disentangling their latent representations into the texture, shape and identity factors, they are fundamentally limited in modeling the nonlinear age-related transformation on texture and shape whilst preserving identity. In this work, a novel LFS model is proposed to disentangle the key face characteristics including shape, texture and identity so that the unique shape and texture age transformations can be modeled effectively. This is achieved by extracting shape, texture and identity features separately from an encoder. Critically, two transformation modules, one conditional convolution based and the other channel attention based, are designed for modeling the nonlinear shape and texture feature transformations respectively. This is to accommodate their rather distinct aging processes and ensure that our synthesized images are both age-sensitive and identity preserving. Extensive experiments show that our LFS model is clearly superior to the state-of-the-art alternatives. Codes and demo are available on our project website: \url{https://senhe.github.io/projects/iccv_2021_lifespan_face}.<br />To appear in ICCV 2021 |
|---|---|
| DOI: | 10.1109/iccv48922.2021.00385 |