Name: Ukcheol Shin
Type: User
Company: Carnegie Mellon University, Robotics Institute
Bio: My research interests lie in machine learning, 3D vision, multi-modal sensor system, robotics computer vision.
Location: 1723 Murray Ave, Pittsburgh, PA 15217
Blog: https://ukcheolshin.github.io/
Ukcheol Shin's Projects
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Official implementation of the paper "Complementary Random Masking for RGB-T Semantic Segmentation."
Deep InfraRed image processing framework
Deep Pose Correction for Visual Localization
Official implementation for "DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning"
Domain-invariant Stereo Matching Networks
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
[ICCV2021] IICNet: A Generic Framework for Reversible Image Conversion
[ECCV'20] Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
KEPCO Motor Control Code
Code for "Self-Supervised 3D Keypoint Learning for Ego-motion Estimation"
Models and examples built with TensorFlow
This is the official GitHub page of the Multi-Spectral Stereo (MS2) dataset described in CVPR 2023 paper.
Neural-Guided RANSAC for Estimating Epipolar Geometry from Sparse Correspondences
Official implementation of the paper "Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment"
A Versatile and Accurate Monocular SLAM
Pyramid Scene Parsing Network
PyTorch로 시작하는 딥러닝 입문 CAMP (2017.7~2017.12) 강의자료
Raspberry pi3에서의 kist의 MK4 Motor & Encoder에 대한 제어코드
Raspberrypi3에서 I2C를 이용한 imu 제어.
Raspberrypi3에서 H/W PWM을 이용한 ws2812b led 모듈 제어.
Realtime Edge Based Visual Odometry for a Monocular Camera
Semi-direct Visual Odometry
Unsupervised Scale-consistent Depth Learning from Video (IJCV2021 & NeurIPS 2019)