A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

Official repository for the paper, "Towards Real-world Event-guided Low-light Video Enhancement and Deblurring", ECCV 2024.

Single Image Deraining: A Comprehensive Benchmark Analysis

Keep track of makes, misses, and total shooting percentage using YOLOv8 and openCV in Python.

[CVPR 2025 Highlight] X-Dyna: Expressive Dynamic Human Image Animation

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Unofficial PyTorch implementation of Google AI's VoiceFilter system

You can find the speech algorithms you want here

Noise supression using deep filtering

SpeechDenoiser: Real-Time Speech Denoising with ONNX Welcome to SpeechDenoiser, a simple and effective solution for real-time speech denoising using an ONNX model. This repository contains everythi…

c# library for decoding paraformer, sensevoice Models，used in speech recognition (ASR)

Production First and Production Ready End-to-End Speech Recognition Toolkit

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS…

Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything

Open and efficient video watermarking

使用YOLOv5+DeepLabV3Plus实现仪表的检测、指针表盘分割和刻度读数识别

使用YoloX+DeepLabV3Plus实现仪表的检测、指针表盘分割和刻度读数识别（借助ncnn框架）

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021

文档方向分类

修正文档扭曲/模糊/阴影等情况，使用onnx模型简单轻量部署，未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We will continue to follow and integrate the latest and best docu…

Memory-Guided Diffusion for Expressive Talking Video Generation