Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2601.01950 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914233738854400 |
|---|---|
| author | Wang, Meng Dai, Wenjing Zhang, Jiawan Guo, Xiaojie |
| author_facet | Wang, Meng Dai, Wenjing Zhang, Jiawan Guo, Xiaojie |
| contents | Although recent approaches to face normal estimation have achieved promising results, their effectiveness heavily depends on large-scale paired data for training. This paper concentrates on relieving this requirement via developing a coarse-to-fine normal estimator. Concretely, our method first trains a neat model from a small dataset to produce coarse face normals that perform as guidance (called exemplars) for the following refinement. A self-attention mechanism is employed to capture long-range dependencies, thus remedying severe local artifacts left in estimated coarse facial normals. Then, a refinement network is customized for the sake of mapping input face images together with corresponding exemplars to fine-grained high-quality facial normals. Such a logical function split can significantly cut the requirement of massive paired data and computational resource. Extensive experiments and ablation studies are conducted to demonstrate the efficacy of our design and reveal its superiority over state-of-the-art methods in terms of both training expense as well as estimation quality. Our code and models are open-sourced at: https://github.com/AutoHDR/FNR2R.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01950 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Face Normal Estimation from Rags to Riches Wang, Meng Dai, Wenjing Zhang, Jiawan Guo, Xiaojie Computer Vision and Pattern Recognition Although recent approaches to face normal estimation have achieved promising results, their effectiveness heavily depends on large-scale paired data for training. This paper concentrates on relieving this requirement via developing a coarse-to-fine normal estimator. Concretely, our method first trains a neat model from a small dataset to produce coarse face normals that perform as guidance (called exemplars) for the following refinement. A self-attention mechanism is employed to capture long-range dependencies, thus remedying severe local artifacts left in estimated coarse facial normals. Then, a refinement network is customized for the sake of mapping input face images together with corresponding exemplars to fine-grained high-quality facial normals. Such a logical function split can significantly cut the requirement of massive paired data and computational resource. Extensive experiments and ablation studies are conducted to demonstrate the efficacy of our design and reveal its superiority over state-of-the-art methods in terms of both training expense as well as estimation quality. Our code and models are open-sourced at: https://github.com/AutoHDR/FNR2R.git. |
| title | Face Normal Estimation from Rags to Riches |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.01950 |