PortraVec: Image-Based Portrait Vectorization with Text-Guided Manipulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914513956110336 |
|---|---|
| author | Liang, Yiqi Liu, Ying Long, Dandan Li, Ruihui |
| author_facet | Liang, Yiqi Liu, Ying Long, Dandan Li, Ruihui |
| contents | While portrait sketch generation is a special task in sketch synthesis, most existing methods are pixel-based, limiting their interpretability and editability. With the rise of vector generation techniques, representing sketches using vector elements may provide more flexible manipulation. However, due to the overlapping nature of vector graphics and the coarse detail modeling, existing vectorization methods struggle to capture facial integrity and fine-grained details, and lack semantic control. To address these issues, we propose PortraVec, a framework for converting pixel-based portrait images into vector sketches with text control. Specifically, we propose a two-stage image-guided generation module using Attention-aware Offset Sampling to capture face structure while correcting detail deviations, and a text-guided manipulation module based on Region-based Parameter Freezing to enable local semantic editing while maintaining global consistency. Experiments show that PortraVec achieves superior structural consistency, visual fidelity, and semantic controllability compared to state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04182 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PortraVec: Image-Based Portrait Vectorization with Text-Guided Manipulation Liang, Yiqi Liu, Ying Long, Dandan Li, Ruihui Computer Vision and Pattern Recognition While portrait sketch generation is a special task in sketch synthesis, most existing methods are pixel-based, limiting their interpretability and editability. With the rise of vector generation techniques, representing sketches using vector elements may provide more flexible manipulation. However, due to the overlapping nature of vector graphics and the coarse detail modeling, existing vectorization methods struggle to capture facial integrity and fine-grained details, and lack semantic control. To address these issues, we propose PortraVec, a framework for converting pixel-based portrait images into vector sketches with text control. Specifically, we propose a two-stage image-guided generation module using Attention-aware Offset Sampling to capture face structure while correcting detail deviations, and a text-guided manipulation module based on Region-based Parameter Freezing to enable local semantic editing while maintaining global consistency. Experiments show that PortraVec achieves superior structural consistency, visual fidelity, and semantic controllability compared to state-of-the-art methods. |
| title | PortraVec: Image-Based Portrait Vectorization with Text-Guided Manipulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.04182 |