High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
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_ | 1866908637389127680 |
|---|---|
| author | Zhang, Feng Deng, Haoyou Li, Zhiqiang Li, Lida Xu, Bin Lu, Qingbo Cao, Zisheng Wei, Minchen Gao, Changxin Sang, Nong Bai, Xiang |
| author_facet | Zhang, Feng Deng, Haoyou Li, Zhiqiang Li, Lida Xu, Bin Lu, Qingbo Cao, Zisheng Wei, Minchen Gao, Changxin Sang, Nong Bai, Xiang |
| contents | Photo enhancement plays a crucial role in augmenting the visual aesthetics of a photograph. In recent years, photo enhancement methods have either focused on enhancement performance, producing powerful models that cannot be deployed on edge devices, or prioritized computational efficiency, resulting in inadequate performance for real-world applications. To this end, this paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction. This approach enables fast processing of high-resolution images while also achieving excellent performance. Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images, while incorporating two distinct weight fusion strategies to achieve coarse global image enhancement. To implement this strategy, we designed a spatial-frequency transformer weight predictor that effectively extracts the desired distinct weights by leveraging frequency features. Additionally, we apply local Laplacian filters to adaptively refine edge details in high-frequency components. After meticulously redesigning the network structure and transformer model, LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces runtime, with 4K resolution images processed in just 13 ms on a single GPU. Extensive experimental results on two benchmark datasets further show that the proposed approach performs favorably compared to state-of-the-art methods. The source code will be made publicly available at https://github.com/fengzhang427/LLF-LUT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11613 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network Zhang, Feng Deng, Haoyou Li, Zhiqiang Li, Lida Xu, Bin Lu, Qingbo Cao, Zisheng Wei, Minchen Gao, Changxin Sang, Nong Bai, Xiang Computer Vision and Pattern Recognition Photo enhancement plays a crucial role in augmenting the visual aesthetics of a photograph. In recent years, photo enhancement methods have either focused on enhancement performance, producing powerful models that cannot be deployed on edge devices, or prioritized computational efficiency, resulting in inadequate performance for real-world applications. To this end, this paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction. This approach enables fast processing of high-resolution images while also achieving excellent performance. Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images, while incorporating two distinct weight fusion strategies to achieve coarse global image enhancement. To implement this strategy, we designed a spatial-frequency transformer weight predictor that effectively extracts the desired distinct weights by leveraging frequency features. Additionally, we apply local Laplacian filters to adaptively refine edge details in high-frequency components. After meticulously redesigning the network structure and transformer model, LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces runtime, with 4K resolution images processed in just 13 ms on a single GPU. Extensive experimental results on two benchmark datasets further show that the proposed approach performs favorably compared to state-of-the-art methods. The source code will be made publicly available at https://github.com/fengzhang427/LLF-LUT. |
| title | High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.11613 |