Yuxuan Liu
Owen-Liuyuxuan
Ph.D. in ram-lab under supervision from Prof Ming Liu. Now System Engineer in TIER IV
Languages
Top Repositories
Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
unified multi-threading inferencing nodes for monocular 3D object detection, depth prediction and semantic segmentation
Full Scale Monocular Depth Prediction. Official Implementation of "FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving" https://arxiv.org/abs/2304.10719
Sites to share deep learning related papers and their digests
Open source training framework for vision tasks. Scales up on data and scales up on tasks. Official Implementation for https://arxiv.org/abs/2310.00920
A naive ROS interface for visualDet3D.
Repositories
78Use LLM and arxiv reader to obtain arxiv paper every day; Please check Wiki page or the ReadingCollectionWebsite
Sites to share deep learning related papers and their digests
Chat with Local OpenClaw in VSCode
Scrape the official websites for LLM pricing
Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
unified multi-threading inferencing nodes for monocular 3D object detection, depth prediction and semantic segmentation
A full Gemini implementation of paper2slide
Showing the Arxiv word cloud evolution
AI-powered Q&A server for [papers_reading_sharing.github.io](https://owen-liuyuxuan.github.io/papers_reading_sharing.github.io/).
从零手搓Flow Matching（Rectified Flow）-- Enhanced with CFM
No description provided.
training a naive map Transformer
SAM3D Half, tested in 4090 with daily desktop ubuntu memory occupied.
ROS2 Python Package for visualizing KITTI/KITTI360/nuScenes datasets in RVIZ2
Full Scale Monocular Depth Prediction. Official Implementation of "FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving" https://arxiv.org/abs/2304.10719
Extension library of Lanelet2
Vcs2l is a command line tool designed to make working with multiple repositories easier
Fix the parameter creation from schema so that we will not forget adding parameters.
Naive Plan TF
🎯 告别信息过载，AI 助你看懂新闻资讯热点，简单的舆情监控分析 - 多平台热点聚合+基于 MCP 的AI分析工具。监控35个平台（抖音、知乎、B站、华尔街见闻、财联社等），智能筛选+自动推送+AI对话分析（用自然语言深度挖掘新闻：趋势追踪、情感分析、相似检索等13种工具）。支持企业微信/飞书/钉钉/Telegram/邮件/ntfy推送，30秒网页部署，1分钟手机通知，无需编程。支持Docker部署⭐ 让算法为你服务，用AI理解热点
Testing program for high frequency topic message and callback function
This is the codes and images created by Gemini3 Pro as the huarongdao game
No description provided.
No description provided.
1+1 Childhood game in web
Open source training framework for vision tasks. Scales up on data and scales up on tasks. Official Implementation for https://arxiv.org/abs/2310.00920
Visualize KITTI sequences and object detection benchmark on ROS with full tf support.
A naive ROS interface for visualDet3D.
Visualize nuScenes sequences on ROS with full tf support.
The most open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.