2021 IEEE International Conference on Robotics and Automation (ICRA) 2021
DOI: 10.1109/icra48506.2021.9561132
|View full text |Cite
|
Sign up to set email alerts
|

ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
28
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 41 publications
(30 citation statements)
references
References 25 publications
0
28
0
Order By: Relevance
“…The results compare against ANSCH [3] are shown in Table IV. Despite not using depth images as inputs and not finetuned, we find our model to only perform slightly worse than ANSCH [3] and ScrewNet [11] and [12]. It shows that the proposed representation is a promising direction for category-level articulated pose estimation.…”
Section: Articulated Pose Estimationmentioning
confidence: 86%
See 3 more Smart Citations
“…The results compare against ANSCH [3] are shown in Table IV. Despite not using depth images as inputs and not finetuned, we find our model to only perform slightly worse than ANSCH [3] and ScrewNet [11] and [12]. It shows that the proposed representation is a promising direction for category-level articulated pose estimation.…”
Section: Articulated Pose Estimationmentioning
confidence: 86%
“…As for inferring articulated pose from visual data, [12] proposed to use a mixture density network that consumes an RGB-D image to predict the probability of the joint attribute and articulated pose. ScrewNet [11] takes multiple depth images with different articulated poses and the same camera pose as input to predict joint attribute and articulated pose. [33] extended [34] by including reasoning about the applied actions along with the observed motion of the object while estimating its kinematic structure.…”
Section: B Articulated Object Pose Estimationmentioning
confidence: 99%
See 2 more Smart Citations
“…As an example, Anguelov et al [7] decompose an articulated mesh into approximate rigid parts and use Expectation Maximization (EM) to estimate part assignments and transformations. Other recent methods focus on estimating articulation of novel objects though images [8], [9], [10] or physical interaction [11], [12]. For example, Jain et al [13] learn a distribution over articulation model parameters for novel objects with different degrees of freedom.…”
Section: Related Workmentioning
confidence: 99%