Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913283719561216 |
|---|---|
| author | Dong, Runmin Yuan, Shuai Luo, Bin Chen, Mengxuan Zhang, Jinxiao Zhang, Lixian Li, Weijia Zheng, Juepeng Fu, Haohuan |
| author_facet | Dong, Runmin Yuan, Shuai Luo, Bin Chen, Mengxuan Zhang, Jinxiao Zhang, Lixian Li, Weijia Zheng, Juepeng Fu, Haohuan |
| contents | Reference-based super-resolution (RefSR) has the potential to build bridges across spatial and temporal resolutions of remote sensing images. However, existing RefSR methods are limited by the faithfulness of content reconstruction and the effectiveness of texture transfer in large scaling factors. Conditional diffusion models have opened up new opportunities for generating realistic high-resolution images, but effectively utilizing reference images within these models remains an area for further exploration. Furthermore, content fidelity is difficult to guarantee in areas without relevant reference information. To solve these issues, we propose a change-aware diffusion model named Ref-Diff for RefSR, using the land cover change priors to guide the denoising process explicitly. Specifically, we inject the priors into the denoising model to improve the utilization of reference information in unchanged areas and regulate the reconstruction of semantically relevant content in changed areas. With this powerful guidance, we decouple the semantics-guided denoising and reference texture-guided denoising processes to improve the model performance. Extensive experiments demonstrate the superior effectiveness and robustness of the proposed method compared with state-of-the-art RefSR methods in both quantitative and qualitative evaluations. The code and data are available at https://github.com/dongrunmin/RefDiff. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17460 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model Dong, Runmin Yuan, Shuai Luo, Bin Chen, Mengxuan Zhang, Jinxiao Zhang, Lixian Li, Weijia Zheng, Juepeng Fu, Haohuan Image and Video Processing Computer Vision and Pattern Recognition Reference-based super-resolution (RefSR) has the potential to build bridges across spatial and temporal resolutions of remote sensing images. However, existing RefSR methods are limited by the faithfulness of content reconstruction and the effectiveness of texture transfer in large scaling factors. Conditional diffusion models have opened up new opportunities for generating realistic high-resolution images, but effectively utilizing reference images within these models remains an area for further exploration. Furthermore, content fidelity is difficult to guarantee in areas without relevant reference information. To solve these issues, we propose a change-aware diffusion model named Ref-Diff for RefSR, using the land cover change priors to guide the denoising process explicitly. Specifically, we inject the priors into the denoising model to improve the utilization of reference information in unchanged areas and regulate the reconstruction of semantically relevant content in changed areas. With this powerful guidance, we decouple the semantics-guided denoising and reference texture-guided denoising processes to improve the model performance. Extensive experiments demonstrate the superior effectiveness and robustness of the proposed method compared with state-of-the-art RefSR methods in both quantitative and qualitative evaluations. The code and data are available at https://github.com/dongrunmin/RefDiff. |
| title | Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.17460 |