提出可解释的网络统一RAW域图像增强，兼顾效果与部署效率。
RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement
- 通过残差仿射基重建统一去马赛克与增强任务
- 金字塔双线性仿射网格实现全局调色与局部纹理分层建模
- 适合移动端和嵌入式平台，模型轻量且结果可解释
针对RAW域去马赛克、色彩校正与细节增强中存在的模块碎片化、映射不可解释及部署受限问题，本文提出RPBA-Net——一种可解释的残差金字塔双边仿射网络，用于RAW域ISP增强。输入压缩的RAW数据后，该方法通过估计基础RGB表示并学习身份引导的残差仿射修正，实现去马赛克与增强的统一。进一步构建金字塔双边仿射网格，并结合引导驱动的自回归自适应切片与自适应跨层融合，分层建模全局色调恢复与局部纹理增强。此外，引入平滑性、跨尺度一致性与幅度正则项以提升模型稳定性、可控性与结构可解释性。大量实验表明，RPBA-Net在重建保真度与感知质量上超越代表性RAW-to-sRGB方法，达到当前最优水平，同时保持低模型复杂度，具备强移动端与嵌入式平台部署潜力。
原文摘要 · Abstract (English)
To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancement, this paper proposes RPBA-Net, an interpretable residual pyramid bilateral affine network for RAW-domain ISP enhancement. Given packed RAW as input, the method performs residual affine base reconstruction by estimating a base RGB representation and learning identity-guided residual affine corrections, thereby unifying demosaicing and enhancement. It further builds pyramid bilateral affine grids and combines guide-driven autoregressive adaptive slicing with adaptive cross-layer fusion to hierarchically model global tone restoration and local texture enhancement. In addition, smoothness, cross-scale consistency, and magnitude regularization terms are introduced to improve model stability, controllability, and structural interpretability. Extensive experiments demonstrate that RPBA-Net surpasses representative RAW-to-sRGB methods and achieves state-of-the-art performance in reconstruction fidelity and perceptual quality, while maintaining low model complexity and strong deployment potential for mobile and embedded platforms.
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。