vsr

Real-time lip reading: turn a silent video of someone speaking (from a webcam or an .mp4 file) into English text.

[ECCV 2026] NanoVSR: Real-time video super-resolution on edge devices - official PyTorch implementation

A temporal video upscaler based on SPAN

面向 RKNN NPU 部署的轻量级 2× 神经超分辨率（SISR & VSR），基于MLVC端到端重建，支持 RK3576 RK3588 RV1126B

Efficient & Generic Video Super-Resolution

Home Assistant integration for SystemAir SAVE ventilation units

LDIP (Long Distance Information Propagation) VSR and ReBaIR reference-based image SR — unofficial re-implementation

基于Video-subtitle-remover的精细化字幕检测与去除

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

🚀 SynthAVSR is a research framework for training and evaluating audiovisual speech recognition (AVSR) models using synthetic data — with a focus on low-resource languages like Spanish and Catalan.

Web interface for a real-time silent speech recognition tool.

A real-time silent speech recognition tool.

[Interspeech 2024] SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization

ICIP2024 challenge for 360 super resolution

HiRN: Hierarchical Recurrent Neural Network for Video Super-Resolution (VSR) using Two-Stage Feature Evolution - Official Repository (Applied Soft Computing)

HiRN: Hierarchical Recurrent Neural Network for Video Super-Resolution (VSR) using Two-Stage Feature Evolution - Official Repository (Applied Soft Computing)

Group-based Bi-Directional Recurrent Wavelet Neural Network for Efficient Video Super-Resolution (VSR) - Official Repository (Pattern Recognition Letters)

Group-based Bi-Directional Recurrent Wavelet Neural Network for Efficient Video Super-Resolution (VSR) - Official Repository (Pattern Recognition Letters)

This is an official implementation of Video Super-Resolution via a Spatio-Temporal Alignment Network.

Official repository containing code and other material from the paper "Efficient Video Super-Resolution through Recurrent Latent Space Propagation" (https://arxiv.org/abs/1909.08080).