Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image

Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining un...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	International journal of computer vision Jg. 128; H. 5; S. 1331 - 1359
Hauptverfasser:	Grard, Matthieu, Dellandréa, Emmanuel, Chen, Liming
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.05.2020 Springer Springer Nature B.V Springer Verlag
Schriftenreihe:	Special Issue on Deep Learning for Robotic Vision
Schlagworte:	Artificial Intelligence Coders Complexity Computer Imaging Computer Science Computer Vision and Pattern Recognition Datasets Decoding Image annotation Image enhancement Image Processing and Computer Vision Image segmentation Layouts Learning Machine Learning Occlusion Pattern Recognition Pattern Recognition and Graphics Position sensing Representations Special Issue on Deep Learning for Robotic Vision Vision Instance boundary and occlusion detection Domain adaptation Fully convolutional encoder–decoder networks Synthetic data Fully convolutional encoder-decoder networks
ISSN:	0920-5691, 1573-1405
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!