publication . Preprint . 2016

Compressive Image Recovery Using Recurrent Generative Model

Dave, Akshat; Vadathya, Anil Kumar; Mitra, Kaushik;
Open Access English
  • Published: 13 Dec 2016
Abstract
Reconstruction of signals from compressively sensed measurements is an ill-posed problem. In this paper, we leverage the recurrent generative model, RIDE, as an image prior for compressive image reconstruction. Recurrent networks can model long-range dependencies in images and hence are suitable to handle global multiplexing in reconstruction from compressive imaging. We perform MAP inference with RIDE using back-propagation to the inputs and projected gradient method. We propose an entropy thresholding based approach for preserving texture in images well. Our approach shows superior reconstructions compared to recent global reconstruction approaches like D-AMP ...
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
27 references, page 1 of 2

[1] M. Aharon, M. Elad, and A. Bruckstein. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 54(11):4311, 2006. 2

[2] R. G. Baraniuk. Compressive sensing. IEEE signal processing magazine, 24(4), 2007. 5

[3] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising: Can plain neural networks compete with bm3d? In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 2392-2399. IEEE, 2012. 2

[4] E. J. Cande`s, J. Romberg, and T. Tao. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on information theory, 52(2):489-509, 2006. 3

[5] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian. Bm3d image denoising with shape-adaptive principal component analysis. In SPARS'09-Signal Processing with Adaptive Sparse Structured Representations, 2009. 2 [OpenAIRE]

[6] D. L. Donoho, A. Maleki, and A. Montanari. Messagepassing algorithms for compressed sensing. Proceedings of the National Academy of Sciences, 106(45):18914-18919, 2009. 3

[7] M. F. Duarte, M. A. Davenport, D. Takhar, J. N. Laska, T. Sun, K. E. Kelly, R. G. Baraniuk, et al. Single-pixel imaging via compressive sampling. IEEE Signal Processing Magazine, 25(2):83, 2008. 3

[8] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580-587, 2014. 1

[9] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2672-2680, 2014. 2

[10] A. Graves. Neural networks. In Supervised Sequence Labelling with Recurrent Neural Networks, pages 15-35. Springer, 2012. 2, 3

[11] G. E. Hinton, T. J. Sejnowski, and D. H. Ackley. Boltzmann machines: Constraint satisfaction networks that learn. Carnegie-Mellon University, Department of Computer Science Pittsburgh, PA, 1984. 2

[12] D. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. 6

[13] D. P. Kingma and M. Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013. 2

[14] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097-1105, 2012. 1

[15] K. Kulkarni, S. Lohit, P. Turaga, R. Kerviche, and A. Ashok. Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 449-458, 2016. 1, 2

27 references, page 1 of 2
Abstract
Reconstruction of signals from compressively sensed measurements is an ill-posed problem. In this paper, we leverage the recurrent generative model, RIDE, as an image prior for compressive image reconstruction. Recurrent networks can model long-range dependencies in images and hence are suitable to handle global multiplexing in reconstruction from compressive imaging. We perform MAP inference with RIDE using back-propagation to the inputs and projected gradient method. We propose an entropy thresholding based approach for preserving texture in images well. Our approach shows superior reconstructions compared to recent global reconstruction approaches like D-AMP ...
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
27 references, page 1 of 2

[1] M. Aharon, M. Elad, and A. Bruckstein. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 54(11):4311, 2006. 2

[2] R. G. Baraniuk. Compressive sensing. IEEE signal processing magazine, 24(4), 2007. 5

[3] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising: Can plain neural networks compete with bm3d? In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 2392-2399. IEEE, 2012. 2

[4] E. J. Cande`s, J. Romberg, and T. Tao. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on information theory, 52(2):489-509, 2006. 3

[5] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian. Bm3d image denoising with shape-adaptive principal component analysis. In SPARS'09-Signal Processing with Adaptive Sparse Structured Representations, 2009. 2 [OpenAIRE]

[6] D. L. Donoho, A. Maleki, and A. Montanari. Messagepassing algorithms for compressed sensing. Proceedings of the National Academy of Sciences, 106(45):18914-18919, 2009. 3

[7] M. F. Duarte, M. A. Davenport, D. Takhar, J. N. Laska, T. Sun, K. E. Kelly, R. G. Baraniuk, et al. Single-pixel imaging via compressive sampling. IEEE Signal Processing Magazine, 25(2):83, 2008. 3

[8] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580-587, 2014. 1

[9] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2672-2680, 2014. 2

[10] A. Graves. Neural networks. In Supervised Sequence Labelling with Recurrent Neural Networks, pages 15-35. Springer, 2012. 2, 3

[11] G. E. Hinton, T. J. Sejnowski, and D. H. Ackley. Boltzmann machines: Constraint satisfaction networks that learn. Carnegie-Mellon University, Department of Computer Science Pittsburgh, PA, 1984. 2

[12] D. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. 6

[13] D. P. Kingma and M. Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013. 2

[14] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097-1105, 2012. 1

[15] K. Kulkarni, S. Lohit, P. Turaga, R. Kerviche, and A. Ashok. Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 449-458, 2016. 1, 2

27 references, page 1 of 2
Any information missing or wrong?Report an Issue