StableFlow: Real-Time 4K Video Super-Resolution With Robust Feature Propagation

Abstract

Real-time 4K video super-resolution (VSR) requires the effective reuse of temporal information under strict latency constraints, typically relying on temporal alignment and real-time reconstruction. However, imperfect alignment introduces perturbations into the temporal recursion, which can accumulate over time and degrade reconstruction quality—an effect widely observed in recurrent VSR pipelines but rarely analyzed explicitly from a dynamical perspective under real-time constraints. In this work, we formulate real-time VSR inference as a recurrent dynamical process, embedding alignment within the state update. This formulation enables explicit analysis of how alignment-induced perturbations are introduced and propagated during inference. Motivated by this analysis, we propose StableFlow, a stability-guided real-time VSR framework. Specifically, StableFlow introduces an Alignment Gain-aware Alignment Module (AGAM) to enhance the utility of temporally aligned features, a State-aware Perturbation Control Filter (SPCF) to suppress unreliable propagated information, and a Temporal Propagation Control (TPC) loss to regulate long-term recurrent state evolution. Our method combines efficient temporal alignment with state-aware perturbation control and a temporal propagation control loss to stabilize long-term recurrent behavior. Experiments demonstrate that StableFlow achieves real-time 4K performance (over 40 FPS on an NVIDIA RTX 3090) for <inline-formula> <tex-math notation="LaTeX">$4\times $ </tex-math></inline-formula>upscaling from <inline-formula> <tex-math notation="LaTeX">$960\times 540$ </tex-math></inline-formula> inputs to <inline-formula> <tex-math notation="LaTeX">$3840\times 2160$ </tex-math></inline-formula> outputs, with only 321K parameters and 77.45G FLOPs, while maintaining competitive reconstruction quality.