Discovering an Image-Adaptive Coordinate System for Photography Processing
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910780698394624 |
|---|---|
| author | Cui, Ziteng Gu, Lin Harada, Tatsuya |
| author_facet | Cui, Ziteng Gu, Lin Harada, Tatsuya |
| contents | Curve & Lookup Table (LUT) based methods directly map a pixel to the target output, making them highly efficient tools for real-time photography processing. However, due to extreme memory complexity to learn full RGB space mapping, existing methods either sample a discretized 3D lattice to build a 3D LUT or decompose into three separate curves (1D LUTs) on the RGB channels. Here, we propose a novel algorithm, IAC, to learn an image-adaptive Cartesian coordinate system in the RGB color space before performing curve operations. This end-to-end trainable approach enables us to efficiently adjust images with a jointly learned image-adaptive coordinate system and curves. Experimental results demonstrate that this simple strategy achieves state-of-the-art (SOTA) performance in various photography processing tasks, including photo retouching, exposure correction, and white-balance editing, while also maintaining a lightweight design and fast inference speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06448 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Discovering an Image-Adaptive Coordinate System for Photography Processing Cui, Ziteng Gu, Lin Harada, Tatsuya Computer Vision and Pattern Recognition Curve & Lookup Table (LUT) based methods directly map a pixel to the target output, making them highly efficient tools for real-time photography processing. However, due to extreme memory complexity to learn full RGB space mapping, existing methods either sample a discretized 3D lattice to build a 3D LUT or decompose into three separate curves (1D LUTs) on the RGB channels. Here, we propose a novel algorithm, IAC, to learn an image-adaptive Cartesian coordinate system in the RGB color space before performing curve operations. This end-to-end trainable approach enables us to efficiently adjust images with a jointly learned image-adaptive coordinate system and curves. Experimental results demonstrate that this simple strategy achieves state-of-the-art (SOTA) performance in various photography processing tasks, including photo retouching, exposure correction, and white-balance editing, while also maintaining a lightweight design and fast inference speed. |
| title | Discovering an Image-Adaptive Coordinate System for Photography Processing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.06448 |