NTIRE 2025: SIRR in the Wild

M5Dialを使ったシンプルなキー入力デバイス

OBS Studio - Free and open source software for live streaming and screen recording

StreamingVLM: Real-Time Understanding for Infinite Video Streams

This repository contains the trained models and some audio samples for the tPLCnet.

DEIMv2のPythonでのONNX推論サンプル

Visualize ONNX models with model-explorer

[DEIMv2] Real Time Object Detection Meets DINOv3

Reference PyTorch implementation and models for DINOv3

Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"

A beautiful, non-destructive, and GPU-accelerated RAW image editor built with performance in mind.

Multi-Relational Multi-Party Chat Corpus (MRMP): Japanese text-based chat dialogues comprising first-time-meeting and family-included conversations

Real-time & local speech-to-text server.

AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs.

A Git-compatible VCS that is both simple and powerful

Official PyTorch implementation of "PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image", ICCV 2025.

State-of-the-art TTS model under 25MB 😻

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

A real-time and light-weight software for generation of non-linguistic behaviors (turn-taking, backchannel, and head-nodding) in conversational AIs

Glances an Eye on your system. A top/htop alternative for GNU/Linux, BSD, Mac OS and Windows operating systems.

In this repository I have explained the model for face blurring and deblurring.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The code for "Box-supervised Instance Segmentation with Level Set Evolution(ECCV2022)"

This computer vision project focuses on reproducing the Pose2Seg model for pose-based human instance segmentation and adapting it to the Ski2DPose dataset. It includes dataset preprocessing, model …

The paper is explained here: https://towardsdatascience.com/detection-free-human-instance-segmentation-using-pose2seg-and-pytorch-72f48dc4d23e

Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

One summary of efficient segment anything models

A CLI tool for analyzing Claude Code/Codex CLI usage from local JSONL files.

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"