发表机构
Gdańsk University of Technology（格但斯克工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对边缘设备视频超分辨率计算开销大问题，提出NanoVSR架构，利用结构重参数化实现硬件兼容与低开销，通过渐进训练隐式学习时空对齐，在REDS4基准测试中平衡精度与效率，提升边缘设备超分辨率性能。
AI 中文摘要
近期视频超分辨率（VSR）方法严重依赖变压器和显式光流，产生计算开销和定制操作，阻碍在TensorRT等硬件加速器上部署。为此引入NanoVSR，一种为资源受限边缘设备设计的可扩展全卷积架构。通过结构重参数化，推理时可折叠为标准卷积，确保硬件兼容性和低运行时开销。虽无显式运动补偿，但通过渐进训练隐式学习时空对齐保持竞争力。在REDS4基准测试中表现出色，NanoVSR-644k基线在NVIDIA Jetson Orin NX 16GB（25W）上实现28.64 dB PSNR和27.2 FPS，速度大幅提升，扩展的NanoVSR-1.7M变体达到29.15 dB和19.58 FPS吞吐量。
英文摘要
Recent Video Super-Resolution (VSR) methods rely heavily on transformers and explicit optical flow, creating computational overhead and custom operations that hinder deployment on hardware accelerators like TensorRT. To address this, we introduce NanoVSR, a scalable, fully convolutional architecture designed for resource-constrained edge devices. Using structural reparameterization, NanoVSR collapses into standard convolutions during inference, ensuring seamless hardware compatibility and negligible runtime overhead. Furthermore, despite lacking explicit motion compensation, it maintains competitive restoration quality by implicitly learning spatio-temporal alignments through progressive training. Evaluated on the REDS4 benchmark, NanoVSR demonstrates an exceptional balance between accuracy and computational efficiency, significantly improving the trade-off for compact architectures. Our NanoVSR-644k baseline yields 28.64 dB PSNR while delivering 27.2 FPS on the NVIDIA Jetson Orin NX 16GB (25W), offering massive speed gains over heavier models. The scaled NanoVSR-1.7M variant reaches 29.15 dB with a throughput of 19.58 FPS, providing superior, edge-optimized upscaling. Code is available at https://github.com/filippawlicki/nanovsr.
CommentsAccepted to ECCV 2026. This is the pre-review submitted version, not the camera-ready version. The final authenticated version will be available in the ECCV 2026 proceedings
