PhysPose: Refining 6D Object Poses with Physical Constraints
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913766784892928 |
|---|---|
| author | Malenický, Martin Cífka, Martin Fourmy, Médéric Montaut, Louis Carpentier, Justin Sivic, Josef Petrik, Vladimir |
| author_facet | Malenický, Martin Cífka, Martin Fourmy, Médéric Montaut, Louis Carpentier, Justin Sivic, Josef Petrik, Vladimir |
| contents | Accurate 6D object pose estimation from images is a key problem in object-centric scene understanding, enabling applications in robotics, augmented reality, and scene reconstruction. Despite recent advances, existing methods often produce physically inconsistent pose estimates, hindering their deployment in real-world scenarios. We introduce PhysPose, a novel approach that integrates physical reasoning into pose estimation through a postprocessing optimization enforcing non-penetration and gravitational constraints. By leveraging scene geometry, PhysPose refines pose estimates to ensure physical plausibility. Our approach achieves state-of-the-art accuracy on the YCB-Video dataset from the BOP benchmark and improves over the state-of-the-art pose estimation methods on the HOPE-Video dataset. Furthermore, we demonstrate its impact in robotics by significantly improving success rates in a challenging pick-and-place task, highlighting the importance of physical consistency in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23587 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhysPose: Refining 6D Object Poses with Physical Constraints Malenický, Martin Cífka, Martin Fourmy, Médéric Montaut, Louis Carpentier, Justin Sivic, Josef Petrik, Vladimir Computer Vision and Pattern Recognition Robotics Accurate 6D object pose estimation from images is a key problem in object-centric scene understanding, enabling applications in robotics, augmented reality, and scene reconstruction. Despite recent advances, existing methods often produce physically inconsistent pose estimates, hindering their deployment in real-world scenarios. We introduce PhysPose, a novel approach that integrates physical reasoning into pose estimation through a postprocessing optimization enforcing non-penetration and gravitational constraints. By leveraging scene geometry, PhysPose refines pose estimates to ensure physical plausibility. Our approach achieves state-of-the-art accuracy on the YCB-Video dataset from the BOP benchmark and improves over the state-of-the-art pose estimation methods on the HOPE-Video dataset. Furthermore, we demonstrate its impact in robotics by significantly improving success rates in a challenging pick-and-place task, highlighting the importance of physical consistency in real-world applications. |
| title | PhysPose: Refining 6D Object Poses with Physical Constraints |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2503.23587 |