Sökning: id:"swepub:oai:DiVA.org:kth-336565" >
RGB-D-based categor...
RGB-D-based categorical object pose and shape estimation : Methods, datasets, and evaluation
-
- Bruns, Leonard (författare)
- KTH,Robotik, perception och lärande, RPL
-
- Jensfelt, Patric, 1972- (författare)
- KTH,Robotik, perception och lärande, RPL
-
(creator_code:org_t)
- Elsevier BV, 2023
- 2023
- Engelska.
-
Ingår i: Robotics and Autonomous Systems. - : Elsevier BV. - 0921-8890 .- 1872-793X. ; 168
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Recently, various methods for 6D pose and shape estimation of objects at a per-category level have been proposed. This work provides an overview of the field in terms of methods, datasets, and evaluation protocols. First, an overview of existing works and their commonalities and differences is provided. Second, we take a critical look at the predominant evaluation protocol, including metrics and datasets. Based on the findings, we propose a new set of metrics, contribute new annotations for the Redwood dataset, and evaluate state-of-the-art methods in a fair comparison. The results indicate that existing methods do not generalize well to unconstrained orientations and are actually heavily biased towards objects being upright. We provide an easy-to-use evaluation toolbox with well-defined metrics, methods, and dataset interfaces, which allows evaluation and comparison with various state-of-the-art approaches (https://github.com/roym899/pose_and_shape_evaluation).
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Pose estimation
- RGB-D-based perception
- Shape estimation
- Shape reconstruction
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas