{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/f1cbf750\"></iframe>","width":"100%","height":180,"duration":1338,"description":"\n            🤗 Upvotes: 38 | cs.CV\n\n            Authors:\n            Rui Xie, Yinhong Liu, Penghao Zhou, Chen Zhao, Jun Zhou, Kai Zhang, Zhenyu Zhang, Jian Yang, Zhenheng Yang, Ying Tai\n\n            Title:\n            STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution\n\n            Arxiv:\n            http://arxiv.org/abs/2501.02976v1\n\n            Abstract:\n            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 (\\textit{e.g.}, CogVideoX-5B). To enhance the spatio-temporal quality of restored videos, we introduce\\textbf{~\\name} (\\textbf{S}patial-\\textbf{T}emporal \\textbf{A}ugmentation with T2V models for \\textbf{R}eal-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\\textbf{~\\name}~outperforms state-of-the-art methods on both synthetic and real-world datasets.\n            ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}