Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.08564 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912953519833088 |
|---|---|
| author | Afifi, Mahmoud Wang, Zhongling Zhang, Ran Brown, Michael S. |
| author_facet | Afifi, Mahmoud Wang, Zhongling Zhang, Ran Brown, Michael S. |
| contents | This paper presents a modular neural image signal processing (ISP) framework that processes raw inputs and renders high-quality display-referred images. Unlike prior neural ISP designs, our method introduces a high degree of modularity, providing full control over multiple intermediate stages of the rendering process.~This modular design not only achieves high rendering accuracy but also improves scalability, debuggability, generalization to unseen cameras, and flexibility to match different user-preference styles. To demonstrate the advantages of this design, we built a user-interactive photo-editing tool that leverages our neural ISP to support diverse editing operations and picture styles. The tool is carefully engineered to take advantage of the high-quality rendering of our neural ISP and to enable unlimited post-editable re-rendering. Our method is a fully learning-based framework with variants of different capacities, all of moderate size (ranging from ~0.5 M to ~3.9 M parameters for the entire pipeline), and consistently delivers competitive qualitative and quantitative results across multiple test sets. Watch the supplemental video at: https://youtu.be/ByhQjQSjxVM |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_08564 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modular Neural Image Signal Processing Afifi, Mahmoud Wang, Zhongling Zhang, Ran Brown, Michael S. Computer Vision and Pattern Recognition This paper presents a modular neural image signal processing (ISP) framework that processes raw inputs and renders high-quality display-referred images. Unlike prior neural ISP designs, our method introduces a high degree of modularity, providing full control over multiple intermediate stages of the rendering process.~This modular design not only achieves high rendering accuracy but also improves scalability, debuggability, generalization to unseen cameras, and flexibility to match different user-preference styles. To demonstrate the advantages of this design, we built a user-interactive photo-editing tool that leverages our neural ISP to support diverse editing operations and picture styles. The tool is carefully engineered to take advantage of the high-quality rendering of our neural ISP and to enable unlimited post-editable re-rendering. Our method is a fully learning-based framework with variants of different capacities, all of moderate size (ranging from ~0.5 M to ~3.9 M parameters for the entire pipeline), and consistently delivers competitive qualitative and quantitative results across multiple test sets. Watch the supplemental video at: https://youtu.be/ByhQjQSjxVM |
| title | Modular Neural Image Signal Processing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.08564 |