iPhoneBlur: A Difficulty-Stratified Benchmark for Consumer Device Motion Deblurring

TL;DR

iPhoneBlur is a new benchmark with difficulty levels for evaluating consumer device motion deblurring, revealing performance gaps and domain differences that aggregate metrics hide.

Contribution

It introduces a difficulty-stratified benchmark with metadata and validation, enabling detailed assessment of deblurring models on real-world mobile data.

Findings

Models degrade by 7-9 dB from Easy to Hard categories.

Spectral analysis shows synthesized blur mimics authentic motion degradation.

Fine-tuning on domain gap improves performance significantly.

Abstract

Motion blur restoration on consumer mobile devices is typically evaluated using aggregate metrics that obscure performance variation across blur difficulty, masking model behavior under real deployment conditions. This work introduces iPhoneBlur, a difficulty-stratified benchmark of 7,400 image pairs synthesized from high-framerate iPhone 17 Pro videos captured in diverse real-world scenarios. Samples are partitioned into Easy, Medium, and Hard categories through PSNR-guided adaptive temporal windowing, with stratification validated by monotonic 2.2x increase in optical flow magnitude across tiers. Each sample includes comprehensive metadata enabling investigation of ISP-aware and difficulty-adaptive restoration strategies. Spectral analysis confirms synthesized blur exhibits high-frequency suppression patterns consistent with authentic motion degradation. Evaluation of six architectures reveals consistent 7-9 dB performance degradation from Easy to Hard subsets, a substantial gap entirely hidden by aggregate reporting. The benchmark further exposes a domain gap between professional and consumer cameras which targeted fine-tuning substantially recovers. By coupling difficulty stratification with deployment-critical metadata, iPhoneBlur enables systematic assessment of model reliability and failure modes for resource-constrained edge systems.