Image Translation as Diffusion Visual Programmers
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_ | 1866914660538646528 |
|---|---|
| author | Han, Cheng Liang, James C. Wang, Qifan Rabbani, Majid Dianat, Sohail Rao, Raghuveer Wu, Ying Nian Liu, Dongfang |
| author_facet | Han, Cheng Liang, James C. Wang, Qifan Rabbani, Majid Dianat, Sohail Rao, Raghuveer Wu, Ying Nian Liu, Dongfang |
| contents | We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image translation framework. Our proposed DVP seamlessly embeds a condition-flexible diffusion model within the GPT architecture, orchestrating a coherent sequence of visual programs (i.e., computer vision models) for various pro-symbolic steps, which span RoI identification, style transfer, and position manipulation, facilitating transparent and controllable image translation processes. Extensive experiments demonstrate DVP's remarkable performance, surpassing concurrent arts. This success can be attributed to several key features of DVP: First, DVP achieves condition-flexible translation via instance normalization, enabling the model to eliminate sensitivity caused by the manual guidance and optimally focus on textual descriptions for high-quality content generation. Second, the framework enhances in-context reasoning by deciphering intricate high-dimensional concepts in feature spaces into more accessible low-dimensional symbols (e.g., [Prompt], [RoI object]), allowing for localized, context-free editing while maintaining overall coherence. Last but not least, DVP improves systemic controllability and explainability by offering explicit symbolic representations at each programming stage, empowering users to intuitively interpret and modify results. Our research marks a substantial step towards harmonizing artificial image translation processes with cognitive intelligence, promising broader applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09742 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Image Translation as Diffusion Visual Programmers Han, Cheng Liang, James C. Wang, Qifan Rabbani, Majid Dianat, Sohail Rao, Raghuveer Wu, Ying Nian Liu, Dongfang Computer Vision and Pattern Recognition We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image translation framework. Our proposed DVP seamlessly embeds a condition-flexible diffusion model within the GPT architecture, orchestrating a coherent sequence of visual programs (i.e., computer vision models) for various pro-symbolic steps, which span RoI identification, style transfer, and position manipulation, facilitating transparent and controllable image translation processes. Extensive experiments demonstrate DVP's remarkable performance, surpassing concurrent arts. This success can be attributed to several key features of DVP: First, DVP achieves condition-flexible translation via instance normalization, enabling the model to eliminate sensitivity caused by the manual guidance and optimally focus on textual descriptions for high-quality content generation. Second, the framework enhances in-context reasoning by deciphering intricate high-dimensional concepts in feature spaces into more accessible low-dimensional symbols (e.g., [Prompt], [RoI object]), allowing for localized, context-free editing while maintaining overall coherence. Last but not least, DVP improves systemic controllability and explainability by offering explicit symbolic representations at each programming stage, empowering users to intuitively interpret and modify results. Our research marks a substantial step towards harmonizing artificial image translation processes with cognitive intelligence, promising broader applications. |
| title | Image Translation as Diffusion Visual Programmers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.09742 |