Dense Semantic Image Segmentation with Objects and Attributes by Shuai Zheng et al.
This paper discusses dense semantic image segmentation with a focus on assigning object class labels and attribute labels to each pixel. The research explores traditional object class segmentation goals and introduces a new goal of segmentation with objects and attributes, detailing the assignment of object class labels and specific attribute labels to pixels. Techniques such as Hierarchical Multi-Label Factorial CRF and Hierarchical Joint Inference are presented and analyzed. The study provides insights into advanced image segmentation methodologies.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Dense semantic image segmentation with objects and attributes Shuai Zheng, Ming-Ming Cheng, Jonathan Warrell, Paul Sturgess, Vibhav Vineet, Carsten Rother*, Philip H. S. Torr Torr Vision Group, University of Oxford *The Technische Universit t Dresden 01/06/2014 Shuai Zheng et al. Dense Semantic Image Segmentation with Objects and Attributes. IEEE CVPR 2014. 1/6
Traditional Goal Object class segmentation Assigning an object class label to each pixel ceiling Wall Cabinet Chair Box Floor 01/06/2014 Shuai Zheng et al. Dense Semantic Image Segmentation with Objects and Attributes. IEEE CVPR 2014. 2/6
Our Goal Segmentation with Objects and Attributes Assigning an object class and a set of attribute labels to each pixel ceiling: painted, textured Wall: Wood, Painted, textured Cabinet: Glossy, shiny, Cube, plastic Chair: Wood Box:cube Floor : pavement, textured, dry, flat 01/06/2014 Shuai Zheng et al. Dense Semantic Image Segmentation with Objects and Attributes. IEEE CVPR 2014. 3/6
Hierarchical Multi-Label Factorial CRF Input Image Object segmentation Grid CRF Fully-connected CRF Hierarchical Fully-connected CRF 01/06/2014 Shuai Zheng et al. Dense Semantic Image Segmentation with Objects and Attributes. IEEE CVPR 2014. 4/6
Hierarchical Joint Inference Picture Painted Wall Chair Floor Object Classes Segmentation Painted attribute segmentation Glossy Input Image Cotton Glossy attribute segmentation Cotton attribute segmentation 01/06/2014 Shuai Zheng et al. Dense Semantic Image Segmentation with Objects and Attributes. IEEE CVPR 2014. 5/6
Thank you! Posters P6 16:30-18:30, Thursday, June 26. http://www.robots.ox.ac.uk/~tvg/ 01/06/2014 Shuai Zheng et al. Dense Semantic Image Segmentation with Objects and Attributes. IEEE CVPR 2014. 6/6
