GrabCut in One Cut

Tang, Meng; Gorelick, Lena; Veksler, Olga; Boykov, Yuri

doi:10.1109/iccv.2013.222

Cited by 202 publications

(211 citation statements)

References 22 publications

Supporting

Mentioning

208

Contrasting

Unclassified

Order By: Relevance

“…As shown in [35], globally optimal S for high-order energy (8) and mixed optimization functional (9) coincide if color models θ are represented by histograms. Since (9) is known to be NP-hard [37], it follows that high-order entropy energy in (8) is also NP-hard.…”

Section: Highmentioning

confidence: 99%

“…Comparisons with the state of the art [35,37] We compare with GrabCut, which as demonstrated in Sec.3.1.2, can be viewed as a bound optimizer. We run both algorithms on the GrabCut dataset [32] (The cross image excluded for comparison with [37]).…”

Section: Appearance Entropy Based Segmentation Robustness Wrt Initimentioning

confidence: 99%

“…3.1.2 Appearance Entropy was proposed for image segmentation in [35] as a general color consistency criterion that can be combined with other standard terms, e.g. boundary smoothness, as in the following binary segmentation energy…”

Section: Highmentioning

confidence: 99%

“…Entropy-based energy (8) from [35] is related to a well-known minimum description length (MDL) functional [42,6] for color model fitting. In particular, for two segments it reduces to a color model fitting energy in GrabCut [32] …”

Section: Highmentioning

confidence: 99%

“…Those energy functions arise naturally in many computer vision and image processing applications. Examples of high-order functions include but are not limited to constraints on segment volume [12,38], clique labeling consistency [13,18,35] and matching target distributions [2,3,12,29]. Pairwise non-submodular energies occur in deconvolution [11], curvature regularization [8,11,28], inpainting [16] and surface registration [16].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Pseudo-bound Optimization for Binary Energies

Tang

Ayed

Boykov

2014

Computer Vision – ECCV 2014

Self Cite

View full text Add to dashboard Cite

Abstract. High-order and non-submodular pairwise energies are important for image segmentation, surface matching, deconvolution, tracking and other computer vision problems. Minimization of such energies is generally NP-hard. One standard approximation approach is to optimize an auxiliary function -an upper bound of the original energy across the entire solution space. This bound must be amenable to fast global solvers. Ideally, it should also closely approximate the original functional, but it is very difficult to find such upper bounds in practice.Our main idea is to relax the upper-bound condition for an auxiliary function and to replace it with a family of pseudo-bounds, which can better approximate the original energy. We use fast polynomial parametric maxflow approach to explore all global minima for our family of submodular pseudo-bounds. The best solution is guaranteed to decrease the original energy because the family includes at least one auxiliary function. Our Pseudo-Bound Cuts algorithm improves the state-of-the-art in many applications: appearance entropy minimization, target distribution matching, curvature regularization, image deconvolution and interactive segmentation.

show abstract

Section: Highmentioning

confidence: 99%

Section: Appearance Entropy Based Segmentation Robustness Wrt Initimentioning

confidence: 99%

Section: Highmentioning

confidence: 99%

Section: Highmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Pseudo-bound Optimization for Binary Energies

Tang

Ayed

Boykov

2014

Computer Vision – ECCV 2014

Self Cite

View full text Add to dashboard Cite

show abstract

Interactive deformation‐driven person silhouette image synthesis

Kong

Wan

Zhang

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

This paper addresses the problem of synthesizing person silhouette images. Previous methods on human‐centric image synthesis deal with normal images taken under consistent lighting conditions. However, a silhouette image has an inconsistent lighting appearance, in which the dark subject and the bright background form a strong contrast. Therefore, it brings great challenges to person silhouette image synthesis. We present a staged method to synthesize realistic person silhouette photos with various poses. The purpose of our method is to give ordinary users the opportunities to interactively adjust the pose of a person in a silhouette photo. The method consists of four main steps: person detection, person analysis, interactive deformation, and image synthesis. To obtain the shape of the target person, we propose a silhouette image segmentation algorithm combined with person detection. Moreover, we also present an effective image inpainting approach to complement a silhouette image with an irregular hole. Experimental results show that the proposed method can generate a set of realistic person silhouette images with interactively changed poses.

show abstract

Figure search by text in large scale digital document collections

Yurtsever

Özcan

Taruz

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary Digital document collections have been created with the transfer of a large number of documents to digital media. These digital archives have provided many benefits to users. As the diversity and size of digital image collections have grown exponentially, it has become increasingly important and difficult to obtain the desired image from them. The images on the document might contain critical information about the subject of it. In this study, an architecture is developed that can work on large‐scale data by creating regular expressions together with full‐text search approaches. The performance of the system has been tested on different academic documents and Elasticsearch and Apache Solr insert times are compared. Compared to Elasticsearch, Apache Solr achieved faster and more successful results.

show abstract

GrabCut in One Cut

Cited by 202 publications

References 22 publications

Pseudo-bound Optimization for Binary Energies

Pseudo-bound Optimization for Binary Energies

Interactive deformation‐driven person silhouette image synthesis

Figure search by text in large scale digital document collections

Contact Info

Product

Resources

About