STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Rui Xie, Yinhong Liu, Zhou, CHEN Zhao, Jun Zhou, Kai Zhang, Zhenyu Zhang, Jian Yang, Zhenheng Yang, Ying Tai

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution: 52 upvotes on Hugging Face Daily Papers, #1 of 19 papers on 2025-01-07. Day-by-day upvote history. It lost 5 votes when the Hub removed votes in bulk.

Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods. However, these models struggle to maintain temporal consistency, as they are trained on static images, limiting their ability to capture temporal dynamics effectively. Integrating text-to-video (T2V) models into video super-resolution for improved temporal modeling is straightforward. However, two key challenges remain: artifacts introduced by complex degradations in real-world scenarios, and compromised fidelity due to the strong generative capacity of powerful T2V models (e.g., CogVideoX-5B). To enhance the spatio-temporal quality of restored videos, we introduce~\name (Spatial-Temporal Augmentation with T2V models for Real-world video super-resolution), a novel approach that leverages T2V models for real-world video super-resolution, achieving realistic spatial details and robust temporal consistency. Specifically, we introduce a Local Information Enhancement Module (LIEM) before the global attention block to enrich local details and mitigate degradation artifacts. Moreover, we propose a Dynamic Frequency (DF) Loss to reinforce fidelity, guiding the model to focus on different frequency components across diffusion steps. Extensive experiments demonstrate~\name~outperforms state-of-the-art methods on both synthetic and real-world datasets.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.