AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution
For video super-resolution practitioners, this method enables high-quality arbitrary-scale upsampling with temporal consistency, overcoming limitations of existing generative and coordinate-based approaches.
AVSR-Diff addresses temporal flickering in arbitrary-scale video super-resolution by decoupling scale-agnostic latent denoising from continuous coordinate rendering, achieving state-of-the-art performance across scales and outperforming fixed-scale generative models on their native resolution.
Diffusion models have significantly advanced video super-resolution (VSR) but remain largely constrained to fixed upsampling scales. Conversely, while coordinate-based arbitrary-scale VSR methods offer scale flexibility, they inherently suffer from severe over-smoothing at large scaling factors. Integrating generative priors with continuous decoding is promising but currently hindered by severe temporal flickering caused by the stochasticity of diffusion sampling. To address this, we propose AVSR-Diff (Arbitrary-scale Video Super-Resolution with Diffusion), a novel decoupled framework that separates scale-agnostic latent denoising from continuous coordinate rendering, effectively avoiding computationally heavy resolution-specific sampling. Our approach introduces a Temporally-Gated Feature Recurrence (TGFR) module to extract strictly aligned, temporally consistent latent priors. Furthermore, we design a continuous video VAE decoder incorporating a Scale-Aware Fourier Refinement (SAFR) module to dynamically adapt frequency components to any target scale. Extensive experiments demonstrate that AVSR-Diff consistently preserves high-frequency details and strong temporal stability across various scales, surpassing state-of-the-art arbitrary-scale baselines. Remarkably, our framework outperforms recent fixed-scale generative models even on their native resolution.