Recent advancements in video super-resolution (VSR) models have demonstrated impressive results in enhancing low-resolution videos. However, due to limitations in adequately controlling the generation process, achieving high fidelity alignment with the low-resolution input while maintaining temporal consistency across frames remains a significant challenge. In this work, we propose Semantic and Temporal Guided Video Super-Resolution (SeTe-VSR), a novel approach that incorporates both semantic and temporal-spatio guidance in the latent diffusion space to address these challenges. By incorporating high-level semantic information and integrating spatial and temporal information, our approach achieves a seamless balance between recovering intricate details and ensuring temporal coherence. Our method not only preserves high-reality visual content but also significantly enhances fidelity. Extensive experiments demonstrate that SeTe-VSR outperforms existing methods in terms of detail recovery and perceptual quality, highlighting its effectiveness for complex video super-resolution tasks.
@article{arxiv.2508.00471,
title = {Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution},
author = {Yiwen Wang and Xinning Chai and Yuhong Zhang and Zhengxue Cheng and Jun Zhao and Rong Xie and Li Song},
journal= {arXiv preprint arXiv:2508.00471},
year = {2025}
}