README.md

metadata

title: 'NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices'
emoji: 🔍
colorFrom: yellow
colorTo: green
sdk: gradio
sdk_version: 6.20.0
python_version: '3.12'
app_file: app.py
pinned: false
license: mit
short_description: Real-time 4x video super-resolution on edge devices

NanoVSR — Real-Time 4× Video Super-Resolution on Edge Devices

Interactive demo for NanoVSR (ECCV 2026), a fully convolutional, bidirectional-recurrent video super-resolution model built for edge devices. It reaches 28.64 dB on REDS4 at 27 FPS on a Jetson Orin NX (25 W), with no custom CUDA ops — just plain 3×3 convolutions after reparameterization.

Upload a low-resolution clip (or try the built-in REDS4 example) and pick one of four model sizes to see NanoVSR upscale it 4× in real time, with a side-by-side comparison and a before/after slider. Inference runs on Hugging Face ZeroGPU.

Model zoo

Model	Params	REDS4 PSNR/SSIM	Orin NX (FPS)
NanoVSR-226k	226k	28.23 / 0.8057	43.86
NanoVSR-644k (baseline)	644k	28.64 / 0.8215	27.20
NanoVSR-1.7M	1.7M	29.15 / 0.8364	19.58
NanoVSR-5.4M	5.4M	29.73 / 0.8526	8.66

Checkpoints are downloaded on demand from the GitHub releases of the main repo and cached for the lifetime of the Space.

Links

• Paper: arXiv:2607.10495
• Code, training and TensorRT deployment: github.com/filippawlicki/nanovsr

Citation

@misc{pawlicki2026nanovsr,
      title={NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices},
      author={Filip Pawlicki and Marcel Kańduła and Marcin Pucek and Kamil Dobies},
      year={2026},
      eprint={2607.10495},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2607.10495},
}