Official repo for CVPR2024 paper "Single Domain Generalization for Crowd Counting"

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥

Examples built with TensorFlow.js

ECCV24 - Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance

Fast and accurate automatic speech recognition (ASR) for edge devices

Converts between Python dictionaries and JSON to ROS messages.

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

[CVPR 2024] Code release for TransNeXt model

On-device noise suppression powered by deep learning

A curated list of facial expression recognition in both 7-emotion classification and affect estimation.

RT-DETR(v2 ※PyTorch版)をGoogle Colaboratory上で訓練しONNXのファイルをエクスポートするサンプル

RT-DETR(v2)のPythonでのONNX推論サンプル

This is a tool for installing and running DRP-AI TVM in a WSL2 docker environment.

Extension package of Apache TVM (Machine Learning Compiler) for Renesas DRP-AI accelerators powered by Edgecortix MERA(TM) Based Apache TVM version: v0.11.1

End-To-End Deep Learning-based Adaptation Control for Linear Acoustic Echo Cancellation

AEC Challenge

🔉 Play and Record Sound with Python 🐍

SoundFile is an audio library based on libsndfile, CFFI, and NumPy

A Pure-Python Real-Time Audio Library

Code for the paper "AMEGO: Active Memory from long EGOcentric videos" published at ECCV 2024

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

Speex Echo Canceller Python Library

NVIDIA Audio Effects SDK is used to apply effects to audio stream. It provides audio denoising for broadcast use cases with real-time audio processing.

Nvidia Maxine API for .Net

A C#/.NET wrapper around Nvidia's Audio Effects (NV-AFX, NvAudioEffects) C SDK

Real-time video web application with 3D sound.

Multi-Object Tracking with Uncertain Detections [ECCV 2024 UnCV]