LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916408623890432 |
|---|---|
| author | Zhang, Ruida Huang, Ziqin Wang, Gu Zhang, Chenyangguang Di, Yan Zuo, Xingxing Tang, Jiwen Ji, Xiangyang |
| author_facet | Zhang, Ruida Huang, Ziqin Wang, Gu Zhang, Chenyangguang Di, Yan Zuo, Xingxing Tang, Jiwen Ji, Xiangyang |
| contents | While RGBD-based methods for category-level object pose estimation hold promise, their reliance on depth data limits their applicability in diverse scenarios. In response, recent efforts have turned to RGB-based methods; however, they face significant challenges stemming from the absence of depth information. On one hand, the lack of depth exacerbates the difficulty in handling intra-class shape variation, resulting in increased uncertainty in shape predictions. On the other hand, RGB-only inputs introduce inherent scale ambiguity, rendering the estimation of object size and translation an ill-posed problem. To tackle these challenges, we propose LaPose, a novel framework that models the object shape as the Laplacian mixture model for Pose estimation. By representing each point as a probabilistic distribution, we explicitly quantify the shape uncertainty. LaPose leverages both a generalized 3D information stream and a specialized feature stream to independently predict the Laplacian distribution for each point, capturing different aspects of object geometry. These two distributions are then integrated as a Laplacian mixture model to establish the 2D-3D correspondences, which are utilized to solve the pose via the PnP module. In order to mitigate scale ambiguity, we introduce a scale-agnostic representation for object size and translation, enhancing training efficiency and overall robustness. Extensive experiments on the NOCS datasets validate the effectiveness of LaPose, yielding state-of-the-art performance in RGB-based category-level object pose estimation. Codes are released at https://github.com/lolrudy/LaPose |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15727 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation Zhang, Ruida Huang, Ziqin Wang, Gu Zhang, Chenyangguang Di, Yan Zuo, Xingxing Tang, Jiwen Ji, Xiangyang Computer Vision and Pattern Recognition While RGBD-based methods for category-level object pose estimation hold promise, their reliance on depth data limits their applicability in diverse scenarios. In response, recent efforts have turned to RGB-based methods; however, they face significant challenges stemming from the absence of depth information. On one hand, the lack of depth exacerbates the difficulty in handling intra-class shape variation, resulting in increased uncertainty in shape predictions. On the other hand, RGB-only inputs introduce inherent scale ambiguity, rendering the estimation of object size and translation an ill-posed problem. To tackle these challenges, we propose LaPose, a novel framework that models the object shape as the Laplacian mixture model for Pose estimation. By representing each point as a probabilistic distribution, we explicitly quantify the shape uncertainty. LaPose leverages both a generalized 3D information stream and a specialized feature stream to independently predict the Laplacian distribution for each point, capturing different aspects of object geometry. These two distributions are then integrated as a Laplacian mixture model to establish the 2D-3D correspondences, which are utilized to solve the pose via the PnP module. In order to mitigate scale ambiguity, we introduce a scale-agnostic representation for object size and translation, enhancing training efficiency and overall robustness. Extensive experiments on the NOCS datasets validate the effectiveness of LaPose, yielding state-of-the-art performance in RGB-based category-level object pose estimation. Codes are released at https://github.com/lolrudy/LaPose |
| title | LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.15727 |