Title | ||
---|---|---|
Probabilistic Category-Level Pose Estimation via Segmentation and Predicted-Shape Priors. |
Abstract | ||
---|---|---|
We introduce a new method for category-level pose estimation which produces a distribution over predicted poses by integrating 3D shape estimates from a generative object model with segmentation information. Given an input depth-image of an object, our variable-time method uses a mixture density network architecture to produce a multi-modal distribution over 3DOF poses; this distribution is then combined with a prior probability encouraging silhouette agreement between the observed input and predicted object pose. Our approach significantly outperforms the current state-of-the-art in category-level 3DOF pose estimation---which outputs a point estimate and does not explicitly incorporate shape and segmentation information---as measured on the Pix3D and ShapeNet datasets. |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Computer Vision and Pattern Recognition | Journal |
Volume | Citations | PageRank |
abs/1905.12079 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benjamin Burchfiel | 1 | 5 | 1.46 |
George Konidaris | 2 | 801 | 59.30 |