RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution

2026-03-12

AI Summary

This work addresses the challenge of smartphone super-resolution, which is hindered by the scarcity of real paired data in the RAW domain. Existing synthetic degradation models often induce significant domain shift due to their neglect of device-specific characteristics. To overcome this limitation, the authors propose a device-calibrated, fine-grained degradation modeling approach that leverages unprocessing of publicly available rendered images to generate device-specific low-resolution RAW images, thereby constructing realistic paired training data. Abandoning generic degradation priors, the method explicitly models device-dependent blur and noise properties and trains an end-to-end RAW-to-RGB super-resolution network. Experiments on real smartphone data demonstrate that the proposed approach substantially outperforms baseline models employing arbitrary degradation combinations, effectively narrowing the domain gap between synthetic and real-world data.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Computational Photography, Image & Video Synthesis
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via ``unprocessing'' pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image RAW-to-RGB SR model and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.

Problem

• super-resolution
• RAW-domain
• degradation modeling
• domain gap
• smartphone imaging

Innovation

• RAW-domain degradation modeling
• device-specific calibration
• unprocessing pipeline
• realistic super-resolution
• smartphone image enhancement