Lazy Snapping Yin Li Jian Sun ChiKeung Tang HeungYeung Shum Hong Kong University of Science and Technology Microsoft Research Asia a Input image b Object Marking c Boundary editing d Output - Description

In b only 2 yellow lines are drawn to indicate the foreground and another blue line to indicate the background All these lines are far away from th etrue object boundary In c an accurate boundary can be obtained by simply clicking and dragging a few ID: 10936 Download Pdf

Similar presentations

Learning to Detect A Salient Object Tie Liu Jian Sun NanNing Zheng Xiaoou Tang HeungYeung Shum Xian Jiaotong University Microsoft Research Asia Xian P
Learning to Detect A Salient Object Tie Liu Jian Sun NanNing Zheng Xiaoou Tang HeungYeung Shum Xian Jiaotong University Microsoft Research Asia Xian P

R China Beijing PR China Abstract We study visual attention by detecting a salient object in an input image We formulate salient object detec tion as an image segmentation problem where we separate the salient object from the image background We prop

Background Cut Jian Sun Weiwei Zhang Xiaoou Tang HeungYeung Shum Microsoft Research Asia Beijing P
Background Cut Jian Sun Weiwei Zhang Xiaoou Tang HeungYeung Shum Microsoft Research Asia Beijing P

R China jiansun weiweiz xitang and hshum microsoftcom Abstract In this paper we introduce background cut a high quality and real time foreground layer extraction algorithm From a single video sequence with a moving foreground object and stationary

Guided Image Filtering Kaiming He Jian Sun and Xiaoou Tang Department of Information Engineering The Chinese University of Hong Kong Microsoft Research Asia Shenzhen Institutes of Advanced Technolog
Guided Image Filtering Kaiming He Jian Sun and Xiaoou Tang Department of Information Engineering The Chinese University of Hong Kong Microsoft Research Asia Shenzhen Institutes of Advanced Technolog

In this paper we propose a novel type of explicit image 64257l ter guided 64257lter Derived from a local linear model the guided 64257lter generates the 64257ltering output by considering the content of a guidance image which can be the input imag

Image Hallucination with Primal Sketch Priors Jian Sun NanNing Zheng Hai Tao HeungYeung Shum The Institute of AI and Robotics Department of C
Image Hallucination with Primal Sketch Priors Jian Sun NanNing Zheng Hai Tao HeungYeung Shum The Institute of AI and Robotics Department of C

E Microsoft Research Asia Xian Jiaotong University Univ of California SC No49 Zhichun Road Xian China 710049 Santa Cruz CA 95064 Beijing China 100080 sj nnzheng aiarxjtueducn taosoeucscedu hshummicrosoftcom Abstract In this paper we propose a Bayesia

Image Hallucination with Primal Sketch Priors Jian Sun NanNing Zheng Hai Tao HeungYeung Shum The Institute of AI and Robotics Department of C
Image Hallucination with Primal Sketch Priors Jian Sun NanNing Zheng Hai Tao HeungYeung Shum The Institute of AI and Robotics Department of C

E Microsoft Research Asia Xian Jiaotong University Univ of California SC No49 Zhichun Road Xian China 710049 Santa Cruz CA 95064 Beijing China 100080 sj nnzheng aiarxjtueducn taosoeucscedu hshummicrosoftcom Abstract In this paper we propose a Bayesia

Guided Image Filtering Kaiming He Jian Sun and Xiaoou Tang Department of Information Engineering The Chinese Univer sity of Hong Kong Microsoft Research Asia Shenzhen Institutes of Advanced Technol
Guided Image Filtering Kaiming He Jian Sun and Xiaoou Tang Department of Information Engineering The Chinese Univer sity of Hong Kong Microsoft Research Asia Shenzhen Institutes of Advanced Technol

In this paper we propose a novel type of explicit image 57356l ter guided 57356lter Derived from a local linear model the guided 57356lter generates the 57356ltering output by considering the content of a guidance image which can be the input imag

Single Image Haze Removal Using Dark Channel Prior Kaiming He Department of Information Engineering The Chinese University of Hong Kong Jian Sun Microsoft Research Asia Xiaoou Tang Shenzhen Institute
Single Image Haze Removal Using Dark Channel Prior Kaiming He Department of Information Engineering The Chinese University of Hong Kong Jian Sun Microsoft Research Asia Xiaoou Tang Shenzhen Institute

The dark channel prior is a kind of s tatistics of the hazefree outdoor images It is based on a key observation most local patches in hazefree outdoor images contain some pixels which have very low intensities in at least one color channel Using th

ContentAware Rotation Kaiming He Microsoft Research Asia Huiwen Chang Tsinghua University Jian Sun Microsoft Research Asia Abstract We present an image editing tool called ContentAware Rotation
ContentAware Rotation Kaiming He Microsoft Research Asia Huiwen Chang Tsinghua University Jian Sun Microsoft Research Asia Abstract We present an image editing tool called ContentAware Rotation

Casually shot photos can appear tilted and are often corrected by rotation and cropping This trivial so lution may remove desired content and hurt image integri ty Instead of doing rigid rotation we propose a warping method that creates the percepti

ContentAware Rotation Kaiming He Microsoft Research Asia Huiwen Chang Tsinghua University Jian Sun Microsoft Research Asia Abstract We present an image editing tool called ContentAware Rotation
ContentAware Rotation Kaiming He Microsoft Research Asia Huiwen Chang Tsinghua University Jian Sun Microsoft Research Asia Abstract We present an image editing tool called ContentAware Rotation

Casually shot photos can appear tilted and are often corrected by rotation and cropping This trivial so lution may remove desired content and hurt image integri ty Instead of doing rigid rotation we propose a warping method that creates the percepti

OptimizedProduct Quantization forApproximate Nearest Neighbor Search Tiezheng Ge Kaiming He Qifa Ke Jian Sun University of Science and Technology of China Microsoft Research Asia Microsoft Research S
OptimizedProduct Quantization forApproximate Nearest Neighbor Search Tiezheng Ge Kaiming He Qifa Ke Jian Sun University of Science and Technology of China Microsoft Research Asia Microsoft Research S

The essence of product quantization is to decompose the orig inal highdimensional space into the Cartesian product of a 64257nite number of lowdimensional subspaces that are then quantized separately Optimal space decomposition is im portant for the

252K - views

Lazy Snapping Yin Li Jian Sun ChiKeung Tang HeungYeung Shum Hong Kong University of Science and Technology Microsoft Research Asia a Input image b Object Marking c Boundary editing d Output

Published byphoebe-click

In b only 2 yellow lines are drawn to indicate the foreground and another blue line to indicate the background All these lines are far away from th etrue object boundary In c an accurate boundary can be obtained by simply clicking and dragging a few

Tags : only
Embed :
Pdf Download Link

Download Pdf - The PPT/PDF document " Lazy Snapping Yin Li Jian Sun ..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Lazy Snapping Yin Li Jian Sun ChiKeung Tang HeungYeung Shum Hong Kong University of Science and Technology Microsoft Research Asia a Input image b Object Marking c Boundary editing d Output






Presentation on theme: " Lazy Snapping Yin Li Jian Sun ChiKeung Tang HeungYeung Shum Hong Kong University of Science and Technology Microsoft Research Asia a Input image b Object Marking c Boundary editing d Output "— Presentation transcript: