l-sf

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

yolov10

YOLOv10: Real-Time End-to-End Object Detection

tts-vue

🎤 微软语音合成工具，使用 Electron + Vue + ElementPlus + Vite 构建。

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

HIP

HIP: C++ Heterogeneous-Compute Interface for Portability

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

ChatTTS_colab

🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持流式输出、音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。

awesome-Implicit-NeRF-SLAM

A comprehensive list of Implicit Representations, NeRF and 3D Gaussian Splatting papers relating to SLAM/Robotics domain, including papers, videos, codes, and related websites

surround-view-system-introduction

A full Python implementation for real car surround view system

BungeeNeRF

[ECCV22] BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering

nndeploy

nndeploy是一款模型端到端部署框架。以多端推理以及基于有向无环图模型部署为基础，致力为用户提供跨平台、简单易用、高性能的模型部署体验。

OccNet

[ICCV 2023] OccNet: Scene as Occupancy

Lite-Mono

[CVPR2023] Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation

mega-nerf

HIP-Examples

Examples for HIP

Switch-NeRF

Codes for Switch-NeRF (ICLR 2023)

SimpleOccupancy

(IEEE TIV) A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving

tensorRT_Pro-YOLOv8

This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.

GaussianFormer

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

tensorrt_starter

This repository give a guidline to learn CUDA and TensorRT from the beginning.

mallocvis

allocation visualization in svg graph

onboard_detector

[IEEE RA-L'24] Dynamic Obstacle Detection and Tracking (DODT) algorithm for Autonomous Robots (C++/ROS)

SNI-SLAM

[CVPR'24] SNI-SLAM: Semantic Neural Implicit SLAM

DKT-Stereo

[CVPR'24] Robust Synthetic-to-Real Transfer for Stereo Matching

rknn-3588-npu-yolo-accelerate

rknn-3588部署yolov5，利用线程池实现npu推理加速；Deploying YOLOv5 on RKNN-3588, utilizing a thread pool to achieve NPU inference acceleration.

multi-thread-programming

This is a repository to practice multi-thread programming in C++

FastSAM_onnx_rknn

FastSAM 部署版本，便于移植不同平，部署简单、运行速度快。

ros_rtsp_server

基于live555框架开发的ros2功能包，作为rtsp服务端，推送H264/H265编码视频，客户端可通过url拉取视频。

operators

算子库