paper-with-me

홈 › Papers

Planar Ultrametrics for Image Segmentation

2015-12-01 · NeurIPS 2015 12 · Julian E. Yarkony, Charless Fowlkes

We study the problem of hierarchical clustering on planar graphs. We formulate this in terms of finding the closest ultrametric to a specified set of distances and solve it using an LP relaxation that leverages minimum cost perfect matching as a subroutine to efficiently explore the space of planar partitions. We apply our algorithm to the problem of hierarchical image segmentation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringImage SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Image Stitching Based on Planar Region Consensus

2020-07-06 · Aocheng Li, Jie Guo, Yanwen Guo

Image stitching for two images without a global transformation between them is notoriously difficult. In this paper, noticing the importance of planar structure under perspective geometry, we propose a new image stitchin…

Image StitchingSegmentationSemantic Segmentation

Planar Ultrametric Rounding for Image Segmentation

2015-07-09 · Julian Yarkony, Charless C. Fowlkes

We study the problem of hierarchical clustering on planar graphs. We formulate this in terms of an LP relaxation of ultrametric rounding. To solve this LP efficiently we introduce a dual cutting plane scheme that uses mi…

ClusteringImage SegmentationSegmentationSemantic Segmentation

Next Generation Multicuts for Semi-Planar Graphs

2015-11-06 · Julian Yarkony

We study the problem of multicut segmentation. We introduce modified versions of the Semi-PlanarCC based on bounding Lagrange multipliers. We apply our work to natural image segmentation.

Image SegmentationSegmentationSemantic Segmentation

A Neuronal Planar Modeling for Handwriting Signature based on Automatic Segmentation

2018-03-27 · Imen Abroug Ben Abdelghani, Najwa Essoukri Ben Amara

This paper deals with offline handwriting signature verification.We propose a planar neuronal model of signature image. Planarmodelsare generally based on delimiting homogenous zones ofimages; we propose in this paper an…

PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

2018-04-17 · CVPR 2018 6 · Chen Liu, Jimei Yang, Duygu Ceylan, Ersin Yumer 외

This paper proposes a deep neural network (DNN) for piece-wise planar depthmap reconstruction from a single RGB image. While DNNs have brought remarkable progress to single-image depth prediction, piece-wise planar depth…

Depth EstimationDepth PredictionSegmentation