Waterpixels

Machairas, Vaïa; Faessel, Matthieu; Cárdenas-Peña, David; Chabardès, Théodore; Walter, Thomas; Decencière, Étienne

doi:10.1109/tip.2015.2451011

Cited by 94 publications

(90 citation statements)

References 22 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning image processing and computer vision perspectives, it would be interesting to study the link between the presented methods and superpixels/supervoxels (see for instance [33,34] for computationally efficient, state-of-the art superpixels methods). For the whole resolution loop, solvers and adaptation are linked to an error, fixed by the user and different according to the resolution.…”

Section: Discussionmentioning

confidence: 99%

Direct multiphase mesh generation from 3D images using anisotropic mesh adaptation and a redistancing equation

Zhao

Coupez

Decencière

et al. 2016

Computer Methods in Applied Mechanics and Engineering

View full text Add to dashboard Cite

In this paper, a new methodology to build automatically 3D adapted meshes, ready for numerical simulations and directly from images, is proposed. It is based on the Immersed Image Method, which interpolates the image information on an initial mesh and combines it with parallel automatic anisotropic mesh adaptation with a control of the number of mesh nodes. Simultaneously, a smooth redistancing technique, based on the resolution of a Hamilton-Jacobi equation, is developed to produce phase functions for the objects to be detected in the image. The proposed methodology is applied on mesh generation and in multiphase flow computations based on 2D and 3D images.

show abstract

Section: Discussionmentioning

confidence: 99%

Direct multiphase mesh generation from 3D images using anisotropic mesh adaptation and a redistancing equation

Zhao

Coupez

Decencière

et al. 2016

Computer Methods in Applied Mechanics and Engineering

View full text Add to dashboard Cite

show abstract

“…Moreover, for tracking application, the aim is to find one-to-one superpixel associations across decompositions, so compactness should be high for convex shapes with balanced pixel repartition. In [7], the circularity is also discussed since it does not consider the square as a highly regular shape. Figure 1 compares two decompositions computed with [6] using initial square and hexagonal grids.…”

Section: Figmentioning

confidence: 99%

“…ERGC [15] WP [7] LSC [8] SCALP [11] Fig. 8: Regularity evolution of noisy superpixels computed from [6] for several compactness settings on the BSD.…”

Section: Slic [6]mentioning

confidence: 99%

“…Such local evaluation seems in line with the visual regularity of the graphs (see Figure 6), but it does not consider the global size regularity within the whole decomposition. Although most methods such as [6,7,11] produce superpixels approximately containing the same number of pixels, other methods may produce partitions of irregular sizes [12,14,16]. In Figure 9, we represent an example of SLIC superpixels [6] and standard quadtree partition, which produces larger squares in areas with lower color variance.…”

Section: Global Regularity Evaluationmentioning

confidence: 99%

“…The decomposition of an image into homogeneous areas, called superpixels, has become a very popular pre-processing step in many image processing and computer vision frameworks. For most superpixel-based applications such as object recognition [1,2], labeling [3] or tracking [4,5], the use of regular decompositions [6,7,8,9,10,11] where superpixels roughly have the same size and regular shapes is necessary. With such regularity, accurate superpixel features can be computed and relevant information can be extracted from their boundaries, while with irregular decompositions [12,13,14,15,16], superpixels can have different sizes, noisy boundaries and stretched shapes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust shape regularity criteria for superpixel evaluation

Giraud¹,

Ta²,

Papadakis³

2017

2017 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Regular decompositions are necessary for most superpixelbased object recognition or tracking applications. So far in the literature, the regularity or compactness of a superpixel shape is mainly measured by its circularity. In this work, we first demonstrate that such measure is not adapted for superpixel evaluation, since it does not directly express regularity but circular appearance. Then, we propose a new metric that considers several shape regularity aspects: convexity, balanced repartition, and contour smoothness. Finally, we demonstrate that our measure is robust to scale and noise and enables to more relevantly compare superpixel methods.

show abstract

Superpixel Sampling Networks

Jampani

Sun

Liu

et al. 2018

Lecture Notes in Computer Science

204

163

View full text Add to dashboard Cite

Superpixels provide an efficient low/mid-level representation of image data, which greatly reduces the number of image primitives for subsequent vision tasks. Existing superpixel algorithms are not differentiable, making them difficult to integrate into otherwise end-to-end trainable deep neural networks. We develop a new differentiable model for superpixel sampling that leverages deep networks for learning superpixel segmentation. The resulting Superpixel Sampling Network (SSN) is end-to-end trainable, which allows learning task-specific superpixels with flexible loss functions and has fast runtime. Extensive experimental analysis indicates that SSNs not only outperform existing superpixel algorithms on traditional segmentation benchmarks, but can also learn superpixels for other tasks. In addition, SSNs can be easily integrated into downstream deep networks resulting in performance improvements. Fig. 1:Overview of Superpixel Sampling Networks. A given image is first passed onto a deep network that extracts features at each pixel, which are then used by differentiable SLIC to generate the superpixels. Shown here are a couple of example SSN generated task-specific superpixels for semantic segmentation and optical flow.non-differentiable and thus using superpixels in deep networks introduces nondifferentiable modules in otherwise end-to-end trainable network architectures.In this work, we alleviate the second issue by proposing a new deep differentiable algorithm for superpixel segmentation. We start by revisiting the widely-used Simple Linear Iterative Clustering (SLIC) superpixel algorithm [1] and turn it into a differentiable algorithm by relaxing the nearest neighbor constraints present in SLIC. This new differentiable algorithm allows for end-to-end training and enables us to leverage powerful deep networks for learning superpixels instead of using traditional hand-crafted features. This combination of a deep network with differentiable SLIC forms our end-to-end trainable superpixel algorithm which we call Superpixel Sampling Network (SSN). Fig. 1 shows an overview of the proposed SSN. A given input image is first passed through a deep network producing features at each pixel. These deep features are then passed onto the differentiable SLIC, which performs iterative clustering, resulting in the desired superpixels. The entire network is end-to-end trainable. The differentiable nature of SSN allows the use of flexible loss functions for learning task-specific superpixels. Fig. 1 shows some sample SSN generated superpixels.Experimental results on 3 different segmentation benchmark datasets including BSDS500 [4], Cityscapes [10] and PascalVOC [11] indicate that the proposed superpixel sampling network (SSN) performs favourably against existing prominent superpixel algorithms, while also being faster. We also demonstrate that by simply integrating our SSN framework into an existing semantic segmentation network [13] that uses superpixels, performance improvements are achieved. In addition, we demonstrate the flex...

show abstract

Waterpixels

Cited by 94 publications

References 22 publications

Direct multiphase mesh generation from 3D images using anisotropic mesh adaptation and a redistancing equation

Direct multiphase mesh generation from 3D images using anisotropic mesh adaptation and a redistancing equation

Robust shape regularity criteria for superpixel evaluation

Superpixel Sampling Networks

Contact Info

Product

Resources

About