Picture for Haoyi Zhu

Haoyi Zhu

Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning

Add code
Nov 21, 2024
Viaarxiv icon

DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild

Add code
Nov 20, 2024
Figure 1 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Figure 2 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Figure 3 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Figure 4 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Viaarxiv icon

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

Add code
Oct 10, 2024
Figure 1 for SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
Figure 2 for SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
Figure 3 for SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
Figure 4 for SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
Viaarxiv icon

Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning

Add code
Feb 04, 2024
Viaarxiv icon

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

Add code
Oct 13, 2023
Figure 1 for PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Figure 2 for PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Figure 3 for PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Figure 4 for PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Viaarxiv icon

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

Add code
Oct 12, 2023
Figure 1 for UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Figure 2 for UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Figure 3 for UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Figure 4 for UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Viaarxiv icon

RH20T: A Robotic Dataset for Learning Diverse Skills in One-Shot

Add code
Jul 02, 2023
Viaarxiv icon

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

Add code
Nov 07, 2022
Figure 1 for AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
Figure 2 for AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
Figure 3 for AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
Figure 4 for AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
Viaarxiv icon

X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\circ} $ Insufficient RGB-D Views

Add code
Oct 11, 2022
Figure 1 for X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\circ} $ Insufficient RGB-D Views
Figure 2 for X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\circ} $ Insufficient RGB-D Views
Figure 3 for X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\circ} $ Insufficient RGB-D Views
Figure 4 for X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\circ} $ Insufficient RGB-D Views
Viaarxiv icon

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Add code
Jun 17, 2022
Figure 1 for MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Figure 2 for MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Figure 3 for MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Figure 4 for MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Viaarxiv icon