Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.14249 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912039868301312 |
|---|---|
| author | Lu, Yiren Wei, Huawei |
| author_facet | Lu, Yiren Wei, Huawei |
| contents | This is a challenge report of the ECCV 2022 WCPA Challenge, Face Reconstruction Track. Inside this report is a brief explanation of how we accomplish this challenge. We design a two-branch network to accomplish this task, whose roles are Face Reconstruction and Face Landmark Detection. The former outputs canonical 3D face coordinates. The latter outputs pixel coordinates, i.e. 2D mapping of 3D coordinates with head pose and perspective projection. In addition, we utilize a differentiable PnP (Perspective-n-Points) layer to finetune the outputs of the two branch. Our method achieves very competitive quantitative results on the MVP-Human dataset and wins a $3^{rd}$ prize in the challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14249 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | End to End Face Reconstruction via Differentiable PnP Lu, Yiren Wei, Huawei Computer Vision and Pattern Recognition This is a challenge report of the ECCV 2022 WCPA Challenge, Face Reconstruction Track. Inside this report is a brief explanation of how we accomplish this challenge. We design a two-branch network to accomplish this task, whose roles are Face Reconstruction and Face Landmark Detection. The former outputs canonical 3D face coordinates. The latter outputs pixel coordinates, i.e. 2D mapping of 3D coordinates with head pose and perspective projection. In addition, we utilize a differentiable PnP (Perspective-n-Points) layer to finetune the outputs of the two branch. Our method achieves very competitive quantitative results on the MVP-Human dataset and wins a $3^{rd}$ prize in the challenge. |
| title | End to End Face Reconstruction via Differentiable PnP |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.14249 |