# RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement

arXiv: https://arxiv.org/abs/2605.03626 · HTML: https://mlsanity.com/paper/2605.03626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [AIM 2020 Challenge on Learned Image Signal Processing Pipeline](https://mlsanity.com/paper/2011.04994/) (2020)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [AWNet: Attentive Wavelet Network for Image ISP](https://mlsanity.com/paper/2008.09228/) (2020)
- [Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.07809/) (2021)
- [ParamISP: Learned Forward and Inverse ISPs using Camera Parameters](https://mlsanity.com/paper/2312.13313/) (2023)
- [Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain](https://mlsanity.com/paper/2401.02161/) (2024)
- [PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing](https://mlsanity.com/paper/2104.02895/) (2021)
- [W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mapping](https://mlsanity.com/paper/1911.08656/) (2019)
- [ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color Consistency](https://mlsanity.com/paper/2503.19283/) (2025)
- [RMFA-Net: A Neural ISP for Real RAW to RGB Image Reconstruction](https://mlsanity.com/paper/2406.11469/) (2024)
- [Del-Net: A Single-Stage Network for Mobile Camera ISP](https://mlsanity.com/paper/2108.01623/) (2021)
- [Image Enhancement via Bilateral Learning](https://mlsanity.com/paper/2112.03888/) (2021)
- [LW-ISP: A Lightweight Model with ISP and Deep Learning](https://mlsanity.com/paper/2210.03904/) (2022)

## Abstract (arXiv)

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.