High-resolution open-vocabulary object 6D pose estimation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914866193760256 |
|---|---|
| author | Corsetti, Jaime Boscaini, Davide Giuliari, Francesco Oh, Changjae Cavallaro, Andrea Poiesi, Fabio |
| author_facet | Corsetti, Jaime Boscaini, Davide Giuliari, Francesco Oh, Changjae Cavallaro, Andrea Poiesi, Fabio |
| contents | The generalisation to unseen objects in the 6D pose estimation task is very challenging. While Vision-Language Models (VLMs) enable using natural language descriptions to support 6D pose estimation of unseen objects, these solutions underperform compared to model-based methods. In this work we present Horyon, an open-vocabulary VLM-based architecture that addresses relative pose estimation between two scenes of an unseen object, described by a textual prompt only. We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features. These features are used to extract cross-scene matches for registration. We evaluate our model on a benchmark with a large variety of unseen objects across four datasets, namely REAL275, Toyota-Light, Linemod, and YCB-Video. Our method achieves state-of-the-art performance on all datasets, outperforming by 12.6 in Average Recall the previous best-performing approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16384 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | High-resolution open-vocabulary object 6D pose estimation Corsetti, Jaime Boscaini, Davide Giuliari, Francesco Oh, Changjae Cavallaro, Andrea Poiesi, Fabio Computer Vision and Pattern Recognition The generalisation to unseen objects in the 6D pose estimation task is very challenging. While Vision-Language Models (VLMs) enable using natural language descriptions to support 6D pose estimation of unseen objects, these solutions underperform compared to model-based methods. In this work we present Horyon, an open-vocabulary VLM-based architecture that addresses relative pose estimation between two scenes of an unseen object, described by a textual prompt only. We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features. These features are used to extract cross-scene matches for registration. We evaluate our model on a benchmark with a large variety of unseen objects across four datasets, namely REAL275, Toyota-Light, Linemod, and YCB-Video. Our method achieves state-of-the-art performance on all datasets, outperforming by 12.6 in Average Recall the previous best-performing approach. |
| title | High-resolution open-vocabulary object 6D pose estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.16384 |