Owen-Liuyuxuan

visualDet3D

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

FSNet

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

papers_reading_sharing.github.io

Sites to share deep learning related papers and their digests

ros2_vision_inference

unified multi-threading inferencing nodes for monocular 3D object detection, depth prediction and semantic segmentation

visionfactory

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

visualDet3D_ros

A naive ROS interface for visualDet3D.

kitti_visualize

Visualize KITTI sequences and object detection benchmark on ROS with full tf support.

nuscenes_visualize

Visualize nuScenes sequences on ROS with full tf support.

kitti360_visualize

Visualize KITTI360 sequences on ROS with full tf support.

monodepth_ros

MonoDepth ROS Node. Used with FSNet https://github.com/Owen-Liuyuxuan/FSNet

Owen-Liuyuxuan.github.io

https://owen-liuyuxuan.github.io/

localPDFSummarizer

a purely simple local attempt for summarizing academic PDF with learning-based tool-box.

ros2_dataset_bridge

ROS2 Python Package for visualizing KITTI/KITTI360/nuScenes datasets in RVIZ2

autoware

Autoware - the world's leading open-source software project for autonomous driving

cross_view_transformers

Cross-view Transformers for real-time Map-view Semantic Segmentation (CVPR 2022 Oral)

ARFlow

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".

autoware.universe

autoware_launch

AutowareArchitectureProposal

This is the source code of the feasibility study for Autoware architecture proposal.

build-your-own-x

🤓 Build your own (insert technology here)

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

cityscapesScripts

README and scripts for the Cityscapes Dataset

dd3d

dgp_visualize

visualizing DGP in ROS. Basically same formats with other visualization methods

ICLR2021-OpenReviewData

Crawl & visualize ICLR papers and reviews.

launch

Tools for launching multiple processes and for writing tests involving multiple processes.

LIGA-Stereo

Code for LIGA-Stereo Detector, ICCV'21

mkdocs-awesome-pages-plugin

An MkDocs plugin that simplifies configuring page titles and their order

MonoFlex

Released code for Objects are Different: Flexible Monocular 3D Object Detection, CVPR21

SUB-Depth

Official implementation of "SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation" 2021