Picture for Stefan Thalhammer

Stefan Thalhammer

From Words to Poses: Enhancing Novel Object Pose Estimation with Vision Language Models

Add code
Sep 09, 2024
Viaarxiv icon

Semi-Autonomous Mobile Search and Rescue Robot for Radiation Disaster Scenarios

Add code
Jun 20, 2024
Viaarxiv icon

Improving 2D-3D Dense Correspondences with Diffusion Models for 6D Object Pose Estimation

Add code
Feb 09, 2024
Viaarxiv icon

STAR: Shape-focused Texture Agnostic Representations for Improved Object Detection and 6D Pose Estimation

Add code
Feb 07, 2024
Viaarxiv icon

ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers

Add code
Sep 21, 2023
Viaarxiv icon

Challenges for Monocular 6D Object Pose Estimation in Robotics

Add code
Jul 22, 2023
Viaarxiv icon

Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects

Add code
May 31, 2023
Viaarxiv icon

Open Challenges for Monocular Single-shot 6D Object Pose Estimation

Add code
Feb 23, 2023
Viaarxiv icon

Grasping the Inconspicuous

Add code
Nov 15, 2022
Viaarxiv icon

COPE: End-to-end trainable Constant Runtime Object Pose Estimation

Add code
Aug 22, 2022
Figure 1 for COPE: End-to-end trainable Constant Runtime Object Pose Estimation
Figure 2 for COPE: End-to-end trainable Constant Runtime Object Pose Estimation
Figure 3 for COPE: End-to-end trainable Constant Runtime Object Pose Estimation
Figure 4 for COPE: End-to-end trainable Constant Runtime Object Pose Estimation
Viaarxiv icon