Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915231255494656 |
|---|---|
| author | Cai, Haoming Huang, Tsung-Wei Gehlot, Shiv Feng, Brandon Y. Shah, Sachin Su, Guan-Ming Metzler, Christopher |
| author_facet | Cai, Haoming Huang, Tsung-Wei Gehlot, Shiv Feng, Brandon Y. Shah, Sachin Su, Guan-Ming Metzler, Christopher |
| contents | Text-to-image diffusion models excel at generating diverse portraits, but lack intuitive shadow control. Existing editing approaches, as post-processing, struggle to offer effective manipulation across diverse styles. Additionally, these methods either rely on expensive real-world light-stage data collection or require extensive computational resources for training. To address these limitations, we introduce Shadow Director, a method that extracts and manipulates hidden shadow attributes within well-trained diffusion models. Our approach uses a small estimation network that requires only a few thousand synthetic images and hours of training-no costly real-world light-stage data needed. Shadow Director enables parametric and intuitive control over shadow shape, placement, and intensity during portrait generation while preserving artistic integrity and identity across diverse styles. Despite training only on synthetic data built on real-world identities, it generalizes effectively to generated portraits with diverse styles, making it a more accessible and resource-friendly solution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21943 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models Cai, Haoming Huang, Tsung-Wei Gehlot, Shiv Feng, Brandon Y. Shah, Sachin Su, Guan-Ming Metzler, Christopher Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Text-to-image diffusion models excel at generating diverse portraits, but lack intuitive shadow control. Existing editing approaches, as post-processing, struggle to offer effective manipulation across diverse styles. Additionally, these methods either rely on expensive real-world light-stage data collection or require extensive computational resources for training. To address these limitations, we introduce Shadow Director, a method that extracts and manipulates hidden shadow attributes within well-trained diffusion models. Our approach uses a small estimation network that requires only a few thousand synthetic images and hours of training-no costly real-world light-stage data needed. Shadow Director enables parametric and intuitive control over shadow shape, placement, and intensity during portrait generation while preserving artistic integrity and identity across diverse styles. Despite training only on synthetic data built on real-world identities, it generalizes effectively to generated portraits with diverse styles, making it a more accessible and resource-friendly solution. |
| title | Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2503.21943 |