Lightweight Unpaired Smartphone ISP Transfer with Semantic Pseudo-Pairing
For participants in the NTIRE 2026 unpaired ISP challenge, this method provides a lightweight and stable solution that improves over baseline without paired data.
The authors tackle unpaired smartphone ISP transfer by using semantic pseudo-pairing with DINOv2 and FGW optimal transport, training a 7K-parameter CNN that achieves 22.569 PSNR, 0.675 SSIM, and 8.067 ΔE on the NTIRE 2026 challenge test set, ranking 3rd in SSIM and ΔE.
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 $ΔE$ on the final hidden test set, significantly improving over the baseline and achieving the 3rd best SSIM and $ΔE$ among all challenge entries. Our code is available at github.com/nuniniyujin/Unpaired-ISP .