NNVISR: Bring Neural Network Video Interpolation and Super Resolution into Video Processing Framework

TL;DR

NNVISR is an open-source plugin that integrates neural network-based video enhancement tasks like denoising, super resolution, and interpolation into the VapourSynth framework, streamlining their application in video processing pipelines.

Contribution

It introduces a flexible, network-agnostic plugin that bridges neural network video enhancement methods with existing video processing workflows.

Findings

Supports various neural network tasks including denoising and super resolution.

Handles network-agnostic frame enhancement seamlessly within VapourSynth.

Open-source release facilitates adoption and further development.

Abstract

We present NNVISR - an open-source filter plugin for the VapourSynth video processing framework, which facilitates the application of neural networks for various kinds of video enhancing tasks, including denoising, super resolution, interpolation, and spatio-temporal super-resolution. NNVISR fills the gap between video enhancement neural networks and video processing pipelines, by accepting any network that enhances a group of frames, and handling all other network agnostic details during video processing. NNVISR is publicly released at https://github.com/tongyuantongyu/vs-NNVISR.