Picture for Ue-Hwan Kim

Ue-Hwan Kim

Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR

Add code
Sep 20, 2022
Figure 1 for Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR
Figure 2 for Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR
Figure 3 for Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR
Figure 4 for Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR
Viaarxiv icon

A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View

Add code
Sep 19, 2022
Figure 1 for A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View
Figure 2 for A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View
Figure 3 for A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View
Figure 4 for A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-View
Viaarxiv icon

Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution

Add code
Apr 19, 2021
Figure 1 for Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
Figure 2 for Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
Figure 3 for Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
Figure 4 for Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
Viaarxiv icon

Revisiting Self-Supervised Monocular Depth Estimation

Add code
Mar 23, 2021
Figure 1 for Revisiting Self-Supervised Monocular Depth Estimation
Figure 2 for Revisiting Self-Supervised Monocular Depth Estimation
Figure 3 for Revisiting Self-Supervised Monocular Depth Estimation
Figure 4 for Revisiting Self-Supervised Monocular Depth Estimation
Viaarxiv icon

ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments

Add code
Mar 09, 2021
Figure 1 for ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments
Figure 2 for ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments
Figure 3 for ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments
Figure 4 for ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments
Viaarxiv icon

A Real-time Vision Framework for Pedestrian Behavior Recognition and Intention Prediction at Intersections Using 3D Pose Estimation

Add code
Sep 23, 2020
Figure 1 for A Real-time Vision Framework for Pedestrian Behavior Recognition and Intention Prediction at Intersections Using 3D Pose Estimation
Figure 2 for A Real-time Vision Framework for Pedestrian Behavior Recognition and Intention Prediction at Intersections Using 3D Pose Estimation
Figure 3 for A Real-time Vision Framework for Pedestrian Behavior Recognition and Intention Prediction at Intersections Using 3D Pose Estimation
Figure 4 for A Real-time Vision Framework for Pedestrian Behavior Recognition and Intention Prediction at Intersections Using 3D Pose Estimation
Viaarxiv icon

s-DRN: Stabilized Developmental Resonance Network

Add code
Dec 18, 2019
Figure 1 for s-DRN: Stabilized Developmental Resonance Network
Figure 2 for s-DRN: Stabilized Developmental Resonance Network
Figure 3 for s-DRN: Stabilized Developmental Resonance Network
Figure 4 for s-DRN: Stabilized Developmental Resonance Network
Viaarxiv icon

SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation

Add code
Nov 16, 2019
Figure 1 for SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Figure 2 for SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Figure 3 for SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Figure 4 for SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Viaarxiv icon

Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection

Add code
Aug 22, 2019
Figure 1 for Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
Figure 2 for Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
Figure 3 for Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
Figure 4 for Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
Viaarxiv icon

3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents

Add code
Aug 14, 2019
Figure 1 for 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
Figure 2 for 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
Figure 3 for 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
Figure 4 for 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
Viaarxiv icon