Crisp Boundary Detection Using Pointwise Mutual Information
Detecting boundaries between semantically meaningful objects in visual scenes is an important component of many vision algorithms. In this paper, we propose a novel method for detecting such boundaries based on a simple underlying principle: pixels belonging to the same object exhibit higher statist...
Main Authors: | Isola, Phillip, Zoran, Daniel, Krishnan, Dilip, Adelson, Edward H. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | en_US |
Published: |
Springer-Verlag
2016
|
Online Access: | http://hdl.handle.net/1721.1/102367 https://orcid.org/0000-0002-1411-6704 https://orcid.org/0000-0003-4988-9771 https://orcid.org/0000-0003-2222-6775 |
Similar Items
-
Learning Ordinal Relationships for Mid-Level Vision
by: Krishnan, Dilip, et al.
Published: (2018) -
Pointwise Convergence of the Schrödinger Flow
by: Compaan, Erin, et al.
Published: (2021) -
Pointwise error estimates and local superconvergence of Jacobi expansions
by: Xiang, Shuhuang, et al.
Published: (2023) -
Contrastive Multiview Coding
by: Tian, Yonglong, et al.
Published: (2022) -
SparkleVision: Seeing the world through random specular microfacets
by: Zhang, Zhengdong, et al.
Published: (2016)