Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.11439 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910903873568768 |
|---|---|
| author | Li, Xirui Herrmann, Charles Chan, Kelvin C. K. Li, Yinxiao Sun, Deqing Ma, Chao Yang, Ming-Hsuan |
| author_facet | Li, Xirui Herrmann, Charles Chan, Kelvin C. K. Li, Yinxiao Sun, Deqing Ma, Chao Yang, Ming-Hsuan |
| contents | Recent progress in image generation has sparked research into controlling these models through condition signals, with various methods addressing specific challenges in conditional generation. Instead of proposing another specialized technique, we introduce a simple, unified framework to handle diverse conditional generation tasks involving a specific image-condition correlation. By learning a joint distribution over a correlated image pair (e.g. image and depth) with a diffusion model, our approach enables versatile capabilities via different inference-time sampling schemes, including controllable image generation (e.g. depth to image), estimation (e.g. image to depth), signal guidance, joint generation (image & depth), and coarse control. Previous attempts at unification often introduce significant complexity through multi-stage training, architectural modification, or increased parameter counts. In contrast, our simple formulation requires a single, computationally efficient training stage, maintains the standard model input, and adds minimal learned parameters (15% of the base model). Moreover, our model supports additional capabilities like non-spatially aligned and coarse conditioning. Extensive results show that our single model can produce comparable results with specialized methods and better results than prior unified methods. We also demonstrate that multiple models can be effectively combined for multi-signal conditional generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11439 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Simple Approach to Unifying Diffusion-based Conditional Generation Li, Xirui Herrmann, Charles Chan, Kelvin C. K. Li, Yinxiao Sun, Deqing Ma, Chao Yang, Ming-Hsuan Computer Vision and Pattern Recognition Recent progress in image generation has sparked research into controlling these models through condition signals, with various methods addressing specific challenges in conditional generation. Instead of proposing another specialized technique, we introduce a simple, unified framework to handle diverse conditional generation tasks involving a specific image-condition correlation. By learning a joint distribution over a correlated image pair (e.g. image and depth) with a diffusion model, our approach enables versatile capabilities via different inference-time sampling schemes, including controllable image generation (e.g. depth to image), estimation (e.g. image to depth), signal guidance, joint generation (image & depth), and coarse control. Previous attempts at unification often introduce significant complexity through multi-stage training, architectural modification, or increased parameter counts. In contrast, our simple formulation requires a single, computationally efficient training stage, maintains the standard model input, and adds minimal learned parameters (15% of the base model). Moreover, our model supports additional capabilities like non-spatially aligned and coarse conditioning. Extensive results show that our single model can produce comparable results with specialized methods and better results than prior unified methods. We also demonstrate that multiple models can be effectively combined for multi-signal conditional generation. |
| title | A Simple Approach to Unifying Diffusion-based Conditional Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.11439 |