NDLI: Spatial Inference Machines

Content Provider	IEEE Xplore Digital Library
Author	Shapovalov, R. Vetrov, D. Kohli, P.
Copyright Year	2013
Description	Author affiliation: Lomonosov Moscow State Univ., Moscow, Russia (Shapovalov, R.; Vetrov, D.) \|\| Microsoft Res. Cambridge, Cambridge, UK (Kohli, P.)
Abstract	This paper addresses the problem of semantic segmentation of 3D point clouds. We extend the inference machines framework of Ross et al. by adding spatial factors that model mid-range and long-range dependencies inherent in the data. The new model is able to account for semantic spatial context. During training, our method automatically isolates and retains factors modelling spatial dependencies between variables that are relevant for achieving higher prediction accuracy. We evaluate the proposed method by using it to predict 17-category semantic segmentations on sets of stitched Kinect scans. Experimental results show that the spatial dependencies learned by our method significantly improve the accuracy of segmentation. They also show that our method outperforms the existing segmentation technique of Koppula et al.
Starting Page	2985
Ending Page	2992
File Size	572404
Page Count	8
File Format	PDF
ISBN	9780769549897
ISSN	10636919
DOI	10.1109/CVPR.2013.384
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-06-23
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Graphical models Training Semantics Computational modeling Three-dimensional displays Predictive models Inference algorithms depth images computer vision semantic segmentation scene understanding inference machines 3D point clouds
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Label Propagation from ImageNet to 3D Point Clouds

Semantic labelling of 3D point clouds using spatial object constraints

Learning message-passing inference machines for structured prediction

Mesh Based Semantic Modelling for Indoor and Outdoor Scenes

Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in RGB-D images

Recognizing Point Clouds Using Conditional Random Fields

Learning strengths and weaknesses of classifiers for RGB-D semantic segmentation

Semantic Urban Maps

Detailed 3D Model Driven Single View Scene Understanding

Spatial Inference Machines

Similar Documents

Label Propagation from ImageNet to 3D Point Clouds

Semantic labelling of 3D point clouds using spatial object constraints

Learning message-passing inference machines for structured prediction

Mesh Based Semantic Modelling for Indoor and Outdoor Scenes

Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in RGB-D images

Recognizing Point Clouds Using Conditional Random Fields

Learning strengths and weaknesses of classifiers for RGB-D semantic segmentation

Semantic Urban Maps

Detailed 3D Model Driven Single View Scene Understanding

Spatial Inference Machines