# Lightweight Unpaired Smartphone ISP Transfer with Semantic Pseudo-Pairing

arXiv: https://arxiv.org/abs/2605.07495 · HTML: https://mlsanity.com/paper/2605.07495/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 32)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [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)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [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)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties](https://mlsanity.com/paper/1811.02834/) (2018)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [Multimodal Style Transfer via Graph Cuts](https://mlsanity.com/paper/1904.04443/) (2019)
- [NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement](https://mlsanity.com/paper/2306.11920/) (2023)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning](https://mlsanity.com/paper/2211.06770/) (2022)
- [Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs](https://mlsanity.com/paper/2404.10700/) (2024)
- [W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mapping](https://mlsanity.com/paper/1911.08656/) (2019)
- [PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networks](https://mlsanity.com/paper/2211.06263/) (2022)
- [MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Rendition](https://mlsanity.com/paper/2401.03220/) (2024)
- [RMFA-Net: A Neural ISP for Real RAW to RGB Image Reconstruction](https://mlsanity.com/paper/2406.11469/) (2024)
- [Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2503.11781/) (2025)
- [Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2003.00187/) (2020)

## Abstract (arXiv)

Unpaired smartphone ISP is a challenging problem due to the lack of scene and color alignment between RAW and target RGB images. Many existing methods either require paired data or rely heavily on adversarial training, which can become unstable in the unpaired setting. In this work, we present a simple and effective approach developed for the NTIRE 2026 Learned Smartphone ISP Challenge with Unpaired Data. Our method first reconstructs larger images from training patches to recover global context. Then, we extract semantic embeddings with DINOv2, and use fused Gromov-Wasserstein (FGW) optimal transport to build pseudo pairs between RAW and RGB images at both image and patch levels. This semantic matching allows us to partially alleviate the unpairedness of the data and build these pseudo input-target pairs. Based on these pseudo pairs, we train a lightweight CNN with only 7K parameters for color rendering. The network is designed to be compact and focus on color transformation rather than structural change, which helps reduce artifacts and improve training stability. Our challenge submission achieves 22.569 PSNR, 0.675 SSIM, and 8.067 Delta E on the final hidden test set, significantly improving over the baseline and achieving the 3rd best SSIM and Delta E among all challenge entries. Our code is available at github.com/nuniniyujin/Unpaired-ISP .