Paper Info
Title
DualPoseNet - Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency.
Abstract
Category-level 6D object pose and size estimation is to predict 9 degrees-of-freedom (9DoF) pose configurations of rotation, translation, and size for object instances observed in single, arbitrary views of cluttered scenes. It extends previous related tasks with learning of the two additional rotation angles. This seemingly small difference poses technical challenges due to the learning and prediction in the full rotation space of SO(3). In this paper, we propose a new method of Dual Pose Network with refined learning of pose consistency for this task, shortened as DualPoseNet. DualPoseNet stacks two parallel pose decoders on top of a shared pose encoder, where the implicit decoder predicts object poses with a working mechanism different from that of the explicit one; they thus impose complementary supervision on the training of pose encoder. We construct the encoder based on spherical convolutions, and design a module of Spherical Fusion wherein for a better embedding of pose-sensitive features from the appearance and shape observations. Given no the testing CAD models, it is the novel introduction of the implicit decoder that enables the refined pose prediction during testing, by enforcing the predicted pose consistency between the two decoders using a self-adaptive loss term. Thorough experiments on the benchmark 9DoF object pose datasets of CAMERA25 and REAL275 confirm efficacy of our designs. DualPoseNet outperforms existing methods with a large margin in the regime of high precision.
Year
DOI
Venue
2021
10.1109/ICCV48922.2021.00354
ICCV
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Jiehong Lin151.82
Zewei Wei200.34
Zhihao Li313617.95
Songcen Xu4928.91
Kui Jia500.34
Yuanqing Li600.34