用模块化设计提升图像处理质量与灵活性
Modular Neural Image Signal Processing
- 分阶段模块化处理原始图像信号，可控性强
- 参数量仅0.5M~3.9M，性能媲美主流方法
- 适合需要可编辑、自定义风格的图像应用
本文提出一种模块化神经图像信号处理（ISP）框架，直接处理原始输入并生成高质量显示参考图像。与以往神经ISP设计不同，该方法引入高度模块化结构，对渲染过程中的多个中间阶段实现完全控制。这种设计不仅保证高还原精度，还提升了可扩展性、可调试性、对未见相机的泛化能力以及匹配不同用户偏好风格的灵活性。为验证其优势，我们构建了一个交互式照片编辑工具，利用该神经ISP支持多样编辑操作和图像风格，并实现无限次可重渲染。所提方法为全学习型框架，具备多种容量变体，整体参数量在0.5M至3.9M之间，且在多个测试集上均表现出色，兼具定性和定量竞争力。视频演示见：https://youtu.be/ByhQjQSjxVM
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。