AI Paper Atlas

Research map / Video / Video segmentation and tracking

NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices

Filip Pawlicki, Marcel Kańduła, Marcin Pucek, Kamil Dobies

ECCV 2026 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fuse multi-branch blocks into single 3x3 conv at inference (ablation)NanoVSR-226k · H100 runtimeruntime (ms/frame): 3.471 -> 1.910Improved
fuse multi-branch blocks into single 3x3 conv at inference (ablation)NanoVSR-226k · REDS4PSNR (dB): 28.23 -> 28.23No clear effect
train with multi-branch reparameterizable blocks instead of single branch (ablation)NanoVSR-226k · REDS4PSNR (dB): 28.13 -> 28.23Improved
train with multi-branch reparameterizable blocks instead of single branch (ablation)NanoVSR-226k · Vid4SSIM: 0.7296 -> 0.7252Hurt
add Vimeo-90K short-sequence pre-training phase (ablation)NanoVSR-226k · Vid4PSNR (dB): 25.17 -> 25.26Improved
add Vimeo-90K short-sequence pre-training phase (ablation)NanoVSR-226k · REDS4PSNR (dB): 28.23 -> 28.23No clear effect
add Vimeo-90K short-sequence pre-training phase (ablation)NanoVSR-226k · Vimeo90K-TPSNR (dB): 34.21 -> 34.31Improved
add SPyNet explicit alignment (ablation)NanoVSR-226k · REDS4PSNR (dB): 28.23 -> 29.44Improved
add SPyNet explicit alignment (ablation)NanoVSR-226k · H100 runtimeruntime (ms/frame): 1.910 -> 3.953Hurt
scale NanoVSR from 22k to 644k parametersNanoVSR · REDS4PSNR (dB): 27.62 -> 28.64Improved
scale NanoVSR from 5.4M to 9.6M parametersNanoVSR · REDS4PSNR (dB): 29.73 -> 29.90No clear effect
run on Jetson Orin NX 16GB (25W) instead of 8GB (15W)NanoVSR-226k · Jetson 180x320FPS: 23.55 -> 43.86Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy