{"ID":2885820,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04485","arxiv_id":"2508.04485","title":"QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution","abstract":"Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment. Quantization offers a potential solution for compressing the VSR model. Nevertheless, quantizing VSR models is challenging due to their temporal characteristics and high fidelity requirements. To address these issues, we propose QuantVSR, a low-bit quantization model for real-world VSR. We propose a spatio-temporal complexity aware (STCA) mechanism, where we first utilize the calibration dataset to measure both spatial and temporal complexities for each layer. Based on these statistics, we allocate layer-specific ranks to the low-rank full-precision (FP) auxiliary branch. Subsequently, we jointly refine the FP and low-bit branches to achieve simultaneous optimization. In addition, we propose a learnable bias alignment (LBA) module to reduce the biased quantization errors. Extensive experiments on synthetic and real-world datasets demonstrate that our method obtains comparable performance with the FP model and significantly outperforms recent leading low-bit quantization methods. Code is available at: https://github.com/bowenchai/QuantVSR.","short_abstract":"Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment. Quantization offers a potential solution for compressing the VSR model. Nevertheless, qua...","url_abs":"https://arxiv.org/abs/2508.04485","url_pdf":"https://arxiv.org/pdf/2508.04485v2","authors":"[\"Bowen Chai\",\"Zheng Chen\",\"Libo Zhu\",\"Wenbo Li\",\"Yong Guo\",\"Yulun Zhang\"]","published":"2025-08-06T14:35:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":611245,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2885820,"paper_url":"https://arxiv.org/abs/2508.04485","paper_title":"QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution","repo_url":"https://github.com/bowenchai/QuantVSR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}