wei.li's repositories
COCO_data_json2xml
把COCO数据集的josn标注转变成VOC数据集xml格式的标注；json数据标注转xml数据标注；把coco数据集json格式转变单张图片对应的xml格式
aerial_navigation_development_environment
Leveraging system development and robot deployment for aerial autonomous navigation.
DCNv4
改善扩散模型u_net
Diff4RLSurvey
强化学习与扩散模型相结合的项目
DiffSynth-Studio
一个优秀的视觉扩散模型，可以实现卡通色、文字转视频
dsv_planner
Dual-Stage Viewpoint Planner for Autonomous Exploration
ETPNav
视觉语言导航
far-planner-with-yolo-complete
A FAR Planner version with yolo to detect object
foc-wheel-legged-robot
Open source materials for a novel structured legged robot, including mechanical design, electronic design, algorithm simulation, and software development. | 一个新型结构的轮腿机器人开源资料，包含机械设计、电子设计、算法仿真、软件开发等材料
Grounded-Segment-Anything
Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
HybridNets_kexinquyufenge
HybridNets: End-to-End Perception Network
InstantID
InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥可以为人生成id并生成不同风格
LLaVA1.5
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
LLMSurvey
一个对大模型进行全面介绍的综述，包括发展、结构、微调、使用等等方面
MiniGPT-4
Open-sourced codes for MiniGPT-4 and MiniGPT-v2
OMG-Seg
One Model For Image/Video/Instractive/Open-Vocabulary Segmentation分割
ONNX-YOLOv7-Object-Detection
Python scripts performing object detection using the YOLOv7 model in ONNX.
parkour
[CoRL 2023] Robot Parkour Learning
RACER
Rapid Exploration with Multiple Unmanned Aerial Vehicles (UAV)
tdle
TDLE: 2D Lidar Exploration with Hierarchical Planning Using Regional Division
TraDeS
Track to Detect and Segment: An Online Multi-Object Tracker (CVPR 2021)
universal_manipulation_interface
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
video_analyst
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
VideoCrafter
VideoCrafter2:通过描述可以生成有趣的视频
YOLOP_Linefit_ground_segmentation
You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）