Picture for Kevin Chen

Kevin Chen

An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas

Add code
May 06, 2024
Viaarxiv icon

Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints

Add code
Mar 12, 2024
Figure 1 for Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints
Figure 2 for Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints
Figure 3 for Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints
Figure 4 for Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints
Viaarxiv icon

Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation

Add code
Sep 02, 2021
Figure 1 for Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation
Figure 2 for Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation
Figure 3 for Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation
Figure 4 for Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation
Viaarxiv icon

Topological Planning with Transformers for Vision-and-Language Navigation

Dec 09, 2020
Figure 1 for Topological Planning with Transformers for Vision-and-Language Navigation
Figure 2 for Topological Planning with Transformers for Vision-and-Language Navigation
Figure 3 for Topological Planning with Transformers for Vision-and-Language Navigation
Figure 4 for Topological Planning with Transformers for Vision-and-Language Navigation
Viaarxiv icon

Learning Object-conditioned Exploration using Distributed Soft Actor Critic

Jul 30, 2020
Figure 1 for Learning Object-conditioned Exploration using Distributed Soft Actor Critic
Figure 2 for Learning Object-conditioned Exploration using Distributed Soft Actor Critic
Figure 3 for Learning Object-conditioned Exploration using Distributed Soft Actor Critic
Figure 4 for Learning Object-conditioned Exploration using Distributed Soft Actor Critic
Viaarxiv icon

A Behavioral Approach to Visual Navigation with Graph Localization Networks

Mar 01, 2019
Figure 1 for A Behavioral Approach to Visual Navigation with Graph Localization Networks
Figure 2 for A Behavioral Approach to Visual Navigation with Graph Localization Networks
Figure 3 for A Behavioral Approach to Visual Navigation with Graph Localization Networks
Figure 4 for A Behavioral Approach to Visual Navigation with Graph Localization Networks
Viaarxiv icon

Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation

Sep 24, 2018
Figure 1 for Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation
Figure 2 for Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation
Figure 3 for Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation
Figure 4 for Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation
Viaarxiv icon

Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings

Add code
Mar 22, 2018
Figure 1 for Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
Figure 2 for Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
Figure 3 for Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
Figure 4 for Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
Viaarxiv icon

Lattice Long Short-Term Memory for Human Action Recognition

Aug 13, 2017
Figure 1 for Lattice Long Short-Term Memory for Human Action Recognition
Figure 2 for Lattice Long Short-Term Memory for Human Action Recognition
Figure 3 for Lattice Long Short-Term Memory for Human Action Recognition
Figure 4 for Lattice Long Short-Term Memory for Human Action Recognition
Viaarxiv icon

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

Add code
Apr 02, 2016
Figure 1 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Figure 2 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Figure 3 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Figure 4 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Viaarxiv icon