DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

The Memory layer for your AI apps

SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

WEB VIDEO PLATFORM是一个基于GB28181-2016标准实现的网络视频平台，支持NAT穿透，支持海康、大华、宇视等品牌的IPC、NVR、DVR接入。支持国标级联，支持rtsp/rtmp等视频流转发到国标平台，支持rtsp/rtmp等推流转发到国标平台。

[NeurIPS 2024] An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Open Source framework for voice and multimodal conversational AI

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

This is an unofficial Implementation

This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

[ICML2024] Official code for GaussianPro: 3D Gaussian Splatting with Progressive Propagation

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

AI Image SIgnal Processing and Computational Photography - Bokeh Rendering , Reversed ISP Challenge, Model-Based Image Signal Processors via Learnable Dictionaries. Official repo for NTIRE and AIM …

⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data

CoTracker is a model for tracking any point (pixel) on a video.

Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, x86_64 servers, webs…

End-to-End Speech Processing Toolkit

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

利用Actions在线云编译openwrt固件，适合官方源码，lede，lienol和immortalwrt源码，支持X86，电视盒子等众多设备！

Imitation Learning algorithms with Co-traing for Mobile ALOHA: ACT, Diffusion Policy, VINN

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

Official implementation of "sound distance estimation" WASPAA 23