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.
-
Updated
Jun 30, 2026 - Python
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.
Efficient & Generic Video Super-Resolution
A real-time silent speech recognition tool.
Latest development of ISR/VSR. Papers and related resources, mainly state-of-the-art and novel works in ICCV, ECCV and CVPR about image super-resolution and video super-resolution.
It is a re-implementation of paper named "Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation" called VSR-DUF model. There are both training codes and test codes about VSR-DUF based tensorflow.
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).
[Interspeech 2024] SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization
[ECCV 2026] NanoVSR: Real-time video super-resolution on edge devices - official PyTorch implementation
This is an official implementation of Video Super-Resolution via a Spatio-Temporal Alignment Network.
Home Assistant integration for SystemAir SAVE ventilation units
Grounding Language Models for Compositional and Spatial Reasoning
Nokia PCE Segment Routing testing
A temporal video upscaler based on SPAN
ICIP2024 challenge for 360 super resolution
Portable Windows mpv setup built around NVIDIA RTX VSR upscaling with crop-aware auto-scaling, plus a dozen+ custom/tuned scripts on top of ModernZ: auto chapter-skip, HDR display switching, native Open File/Folder/URL dialogs, per-site stream quality, organized screenshots, and more.
To associate your repository with the vsr topic, visit your repo's landing page and select "manage topics."