轻量级视频超分模型，4倍分辨率提升仅需103毫秒
RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution
- 可重参数化架构，兼顾清晰度与部署效率
- 180p→720p 4倍超分，PSNR达27.79dB，每10帧仅103毫秒
- 适合移动端实时视频增强，尤其低功耗设备
视频超分辨率（VSR）是视觉计算中的基础挑战，旨在从低质量的低分辨率视频中重建高质量视频序列。尽管深度卷积神经网络在时空超分辨率任务中表现优异，但其高计算开销限制了在资源受限边缘设备上的部署，尤其在对功耗和延迟均有严格要求的实时移动视频处理场景中。本文提出一种可重参数化的高保真视频超分辨率架构 RepNet-VSR，实现4倍实时视频超分。在 REDS 验证集上，该模型将180p视频重构为720p，每10帧处理时间仅103毫秒（基于联发科天玑NPU），PSNR达到27.79dB。竞赛结果表明，该方法在重建质量与部署效率之间取得优异平衡，优于MAI视频超分辨率挑战赛前代冠军算法。
原文摘要 · Abstract (English)
As a fundamental challenge in visual computing, video super-resolution (VSR) focuses on reconstructing highdefinition video sequences from their degraded lowresolution counterparts. While deep convolutional neural networks have demonstrated state-of-the-art performance in spatial-temporal super-resolution tasks, their computationally intensive nature poses significant deployment challenges for resource-constrained edge devices, particularly in real-time mobile video processing scenarios where power efficiency and latency constraints coexist. In this work, we propose a Reparameterizable Architecture for High Fidelity Video Super Resolution method, named RepNet-VSR, for real-time 4x video super-resolution. On the REDS validation set, the proposed model achieves 27.79 dB PSNR when processing 180p to 720p frames in 103 ms per 10 frames on a MediaTek Dimensity NPU. The competition results demonstrate an excellent balance between restoration quality and deployment efficiency. The proposed method scores higher than the previous champion algorithm of MAI video super-resolution challenge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。