MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modeling

TL;DR

This paper introduces MFSR-GAN, a novel multi-frame super-resolution method that uses a synthetic data engine to better model real-world handheld camera noise and motion, resulting in sharper, more realistic high-resolution images.

Contribution

The paper presents a synthetic data engine for training MFSR models and a new GAN architecture that emphasizes a base frame to improve super-resolution quality in real-world scenarios.

Findings

MFSR-GAN outperforms existing methods on synthetic and real data.

Synthetic data engine effectively captures real-world noise and motion.

MFSR-GAN produces sharper, more realistic images.

Abstract

Smartphone cameras have become ubiquitous imaging tools, yet their small sensors and compact optics often limit spatial resolution and introduce distortions. Combining information from multiple low-resolution (LR) frames to produce a high-resolution (HR) image has been explored to overcome the inherent limitations of smartphone cameras. Despite the promise of multi-frame super-resolution (MFSR), current approaches are hindered by datasets that fail to capture the characteristic noise and motion patterns found in real-world handheld burst images. In this work, we address this gap by introducing a novel synthetic data engine that uses multi-exposure static images to synthesize LR-HR training pairs while preserving sensor-specific noise characteristics and image motion found during handheld burst photography. We also propose MFSR-GAN: a multi-scale RAW-to-RGB network for MFSR. Compared to prior approaches, MFSR-GAN emphasizes a "base frame" throughout its architecture to mitigate artifacts. Experimental results on both synthetic and real data demonstrates that MFSR-GAN trained with our synthetic engine yields sharper, more realistic reconstructions than existing methods for real-world MFSR.