FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring

TL;DR

FMA-Net++ is a novel framework that jointly addresses video super-resolution and deblurring by modeling motion and exposure variations, achieving state-of-the-art results on new realistic benchmarks.

Contribution

It introduces a sequence-level architecture with exposure-aware modules that explicitly model coupled motion and exposure effects for improved video restoration.

Findings

Achieves state-of-the-art accuracy and temporal consistency.

Outperforms recent methods in restoration quality and speed.

Generalizes well to real-world videos.

Abstract

Real-world video restoration is plagued by complex degradations from motion coupled with dynamically varying exposure - a key challenge largely overlooked by prior works and a common artifact of auto-exposure or low-light capture. We present FMA-Net++, a framework for joint video super-resolution and deblurring that explicitly models this coupled effect of motion and dynamically varying exposure. FMA-Net++ adopts a sequence-level architecture built from Hierarchical Refinement with Bidirectional Propagation blocks, enabling parallel, long-range temporal modeling. Within each block, an Exposure Time-aware Modulation layer conditions features on per-frame exposure, which in turn drives an exposure-aware Flow-Guided Dynamic Filtering module to infer motion- and exposure-aware degradation kernels. FMA-Net++ decouples degradation learning from restoration: the former predicts exposure- and motion-aware priors to guide the latter, improving both accuracy and efficiency. To evaluate under realistic capture conditions, we introduce REDS-ME (multi-exposure) and REDS-RE (random-exposure) benchmarks. Trained solely on synthetic data, FMA-Net++ achieves state-of-the-art accuracy and temporal consistency on our new benchmarks and GoPro, outperforming recent methods in both restoration quality and inference speed, and generalizes well to challenging real-world videos.