FreeEnricher: Enriching Face Landmarks without Additional Cost
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912451981737984 |
|---|---|
| author | Huang, Yangyu Chen, Xi Kim, Jongyoo Yang, Hao Li, Chong Yang, Jiaolong Chen, Dong |
| author_facet | Huang, Yangyu Chen, Xi Kim, Jongyoo Yang, Hao Li, Chong Yang, Jiaolong Chen, Dong |
| contents | Recent years have witnessed significant growth of face alignment. Though dense facial landmark is highly demanded in various scenarios, e.g., cosmetic medicine and facial beautification, most works only consider sparse face alignment. To address this problem, we present a framework that can enrich landmark density by existing sparse landmark datasets, e.g., 300W with 68 points and WFLW with 98 points. Firstly, we observe that the local patches along each semantic contour are highly similar in appearance. Then, we propose a weakly-supervised idea of learning the refinement ability on original sparse landmarks and adapting this ability to enriched dense landmarks. Meanwhile, several operators are devised and organized together to implement the idea. Finally, the trained model is applied as a plug-and-play module to the existing face alignment networks. To evaluate our method, we manually label the dense landmarks on 300W testset. Our method yields state-of-the-art accuracy not only in newly-constructed dense 300W testset but also in the original sparse 300W and WFLW testsets without additional cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_09525 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | FreeEnricher: Enriching Face Landmarks without Additional Cost Huang, Yangyu Chen, Xi Kim, Jongyoo Yang, Hao Li, Chong Yang, Jiaolong Chen, Dong Computer Vision and Pattern Recognition Artificial Intelligence Graphics Information Retrieval Machine Learning Recent years have witnessed significant growth of face alignment. Though dense facial landmark is highly demanded in various scenarios, e.g., cosmetic medicine and facial beautification, most works only consider sparse face alignment. To address this problem, we present a framework that can enrich landmark density by existing sparse landmark datasets, e.g., 300W with 68 points and WFLW with 98 points. Firstly, we observe that the local patches along each semantic contour are highly similar in appearance. Then, we propose a weakly-supervised idea of learning the refinement ability on original sparse landmarks and adapting this ability to enriched dense landmarks. Meanwhile, several operators are devised and organized together to implement the idea. Finally, the trained model is applied as a plug-and-play module to the existing face alignment networks. To evaluate our method, we manually label the dense landmarks on 300W testset. Our method yields state-of-the-art accuracy not only in newly-constructed dense 300W testset but also in the original sparse 300W and WFLW testsets without additional cost. |
| title | FreeEnricher: Enriching Face Landmarks without Additional Cost |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2212.09525 |