Lp-TV model for structure extraction with end-to-end contour learning

Structure extraction is important for human perception. However, for various textured images, computers can hardly achieve this goal. Despite a plethora of studies to address the challenge, results from most previous methods contain unwanted artifacts and over-smoothed structures. Therefore, to address the weaknesses, we have proposed a variational model with end-to-end contour learning capability. Our formulation dwells in two observations: likelihood for representation of residual textures may be well abstracted using super Gaussian distribution, and edge metrics with semantic meaning may benefit structure preservation. The augmented Lagrangian method is adopted for optimal computation. Compared with classical approaches, our method offers a higher performance in structure extraction, including situations where the images have significant nonuniformity of the scale features.

[1]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Zeev Farbman,et al.  Edge-preserving decompositions for multi-scale tone and detail manipulation , 2008, SIGGRAPH 2008.

[3]  Junfeng Yang,et al.  A New Alternating Minimization Algorithm for Total Variation Image Reconstruction , 2008, SIAM J. Imaging Sci..

[4]  Rob Fergus,et al.  Fast Image Deconvolution using Hyper-Laplacian Priors , 2009, NIPS.

[5]  Frédo Durand,et al.  Image and depth from a conventional camera with a coded aperture , 2007, SIGGRAPH 2007.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  C. Lawrence Zitnick,et al.  Fast Edge Detection Using Structured Forests , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Qingxiong Yang,et al.  Recursive Bilateral Filtering , 2012, ECCV.

[9]  Li Xu,et al.  Structure extraction from texture via relative total variation , 2012, ACM Trans. Graph..

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  David Zhang,et al.  Fast Augmented Lagrangian Method for Image Smoothing with Hyper-Laplacian Gradient Prior , 2014, CCPR.

[12]  Cewu Lu,et al.  Image smoothing via L0 gradient minimization , 2011, ACM Trans. Graph..

[13]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[14]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[15]  Sebastian Nowozin,et al.  Structured Learning and Prediction in Computer Vision , 2011, Found. Trends Comput. Graph. Vis..

[16]  M. Kass,et al.  Smoothed local histogram filters , 2010, SIGGRAPH 2010.

[17]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[18]  David Zhang,et al.  A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse Coding , 2013, 2013 IEEE International Conference on Computer Vision.

[19]  Qi Zhang,et al.  Rolling Guidance Filter , 2014, ECCV.

[20]  Jongmin Baek,et al.  Accelerating spatially varying Gaussian filters , 2010, SIGGRAPH 2010.

[21]  Xue-Cheng Tai,et al.  Augmented Lagrangian Method, Dual Methods, and Split Bregman Iteration for ROF, Vectorial TV, and High Order Models , 2010, SIAM J. Imaging Sci..

[22]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[23]  M. J. D. Powell,et al.  A method for nonlinear constraints in minimization problems , 1969 .

[24]  Tony F. Chan,et al.  Structure-Texture Image Decomposition—Modeling, Algorithms, and Parameter Selection , 2006, International Journal of Computer Vision.

[25]  Raanan Fattal,et al.  Edge-avoiding wavelets and their applications , 2009, ACM Trans. Graph..

[26]  Honglak Lee,et al.  Object Contour Detection with a Fully Convolutional Encoder-Decoder Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Yizhou Yu,et al.  An L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition , 2015, ACM Trans. Graph..

[29]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.