BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917091985063936 |
|---|---|
| author | Huang, Yachuan Luo, Xianrui Wang, Qiwen Shen, Liao Li, Jiaqi Sun, Huiqiang Huang, Zihao Jiang, Wei Cao, Zhiguo |
| author_facet | Huang, Yachuan Luo, Xianrui Wang, Qiwen Shen, Liao Li, Jiaqi Sun, Huiqiang Huang, Zihao Jiang, Wei Cao, Zhiguo |
| contents | Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perform well, rendering controllable bokeh without additional depth inputs remains a significant challenge. Existing classical and neural controllable methods rely on accurate depth maps, while generative approaches often struggle with limited controllability and efficiency. In this paper, we propose BokehFlow, a depth-free framework for controllable bokeh rendering based on flow matching. BokehFlow directly synthesizes photorealistic bokeh effects from all-in-focus images, eliminating the need for depth inputs. It employs a cross-attention mechanism to enable semantic control over both focus regions and blur intensity via text prompts. To support training and evaluation, we collect and synthesize four datasets. Extensive experiments demonstrate that BokehFlow achieves visually compelling bokeh effects and offers precise control, outperforming existing depth-dependent and generative methods in both rendering quality and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15066 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching Huang, Yachuan Luo, Xianrui Wang, Qiwen Shen, Liao Li, Jiaqi Sun, Huiqiang Huang, Zihao Jiang, Wei Cao, Zhiguo Computer Vision and Pattern Recognition Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perform well, rendering controllable bokeh without additional depth inputs remains a significant challenge. Existing classical and neural controllable methods rely on accurate depth maps, while generative approaches often struggle with limited controllability and efficiency. In this paper, we propose BokehFlow, a depth-free framework for controllable bokeh rendering based on flow matching. BokehFlow directly synthesizes photorealistic bokeh effects from all-in-focus images, eliminating the need for depth inputs. It employs a cross-attention mechanism to enable semantic control over both focus regions and blur intensity via text prompts. To support training and evaluation, we collect and synthesize four datasets. Extensive experiments demonstrate that BokehFlow achieves visually compelling bokeh effects and offers precise control, outperforming existing depth-dependent and generative methods in both rendering quality and efficiency. |
| title | BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.15066 |