Diffusion Features for Zero-Shot 6DoF Object Pose Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909403968438272 |
|---|---|
| author | Von Gimborn, Bernd Ausserlechner, Philipp Vincze, Markus Thalhammer, Stefan |
| author_facet | Von Gimborn, Bernd Ausserlechner, Philipp Vincze, Markus Thalhammer, Stefan |
| contents | Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that are effectively general-purpose feature extractors. The characteristics exhibited by these VFMs vary depending on the training data, network architecture, and training paradigm. The prevailing choice in this field are self-supervised Vision Transformers (ViT). This study assesses the influence of Latent Diffusion Model (LDM) backbones on zero-shot pose estimation. In order to facilitate a comparison between the two families of models on a common ground we adopt and modify a recent approach. Therefore, a template-based multi-staged method for estimating poses in a zero-shot fashion using LDMs is presented. The efficacy of the proposed approach is empirically evaluated on three standard datasets for object-specific 6DoF pose estimation. The experiments demonstrate an Average Recall improvement of up to 27% over the ViT baseline. The source code is available at: https://github.com/BvG1993/DZOP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16668 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion Features for Zero-Shot 6DoF Object Pose Estimation Von Gimborn, Bernd Ausserlechner, Philipp Vincze, Markus Thalhammer, Stefan Computer Vision and Pattern Recognition 68T45 I.4.8 Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that are effectively general-purpose feature extractors. The characteristics exhibited by these VFMs vary depending on the training data, network architecture, and training paradigm. The prevailing choice in this field are self-supervised Vision Transformers (ViT). This study assesses the influence of Latent Diffusion Model (LDM) backbones on zero-shot pose estimation. In order to facilitate a comparison between the two families of models on a common ground we adopt and modify a recent approach. Therefore, a template-based multi-staged method for estimating poses in a zero-shot fashion using LDMs is presented. The efficacy of the proposed approach is empirically evaluated on three standard datasets for object-specific 6DoF pose estimation. The experiments demonstrate an Average Recall improvement of up to 27% over the ViT baseline. The source code is available at: https://github.com/BvG1993/DZOP. |
| title | Diffusion Features for Zero-Shot 6DoF Object Pose Estimation |
| topic | Computer Vision and Pattern Recognition 68T45 I.4.8 |
| url | https://arxiv.org/abs/2411.16668 |