MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modeling
This work addresses the challenge of improving image resolution for smartphone users by overcoming limitations in current datasets and methods, representing an incremental advancement in domain-specific super-resolution.
The paper tackles the problem of multi-frame super-resolution for smartphone cameras by introducing a synthetic data engine that preserves real-world noise and motion patterns, and proposing MFSR-GAN, which yields sharper and more realistic reconstructions compared to existing methods.
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.