@inproceedings{Long2015, author = {Long, Mingsheng and Cao, Yue and Wang, Jianmin and Jordan, Michael I.}, title = {Learning Transferable Features with Deep Adaptation Networks}, booktitle = {Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37}, series = {ICML'15}, year = {2015}, location = {Lille, France}, pages = {97--105}, numpages = {9}, url = {http://dl.acm.org/citation.cfm?id=3045118.3045130}, acmid = {3045130}, publisher = {JMLR.org}, } @article{hu2019render4completion, title={Render4Completion: Synthesizing Multi-view Depth Maps for 3D Shape Completion}, author={Hu, Tao and Han, Zhizhong and Shrivastava, Abhinav and Zwicker, Matthias}, journal={arXiv preprint arXiv:1904.08366}, year={2019} } @article{berkhout97eom, abstract = {A review has been given of the surface-related multiple problem by making use of the so-called feedback model. From the resulting equations it has been concluded that the proposed solution does not require any properties of the subsurface. However, source-detector and reflectivity properties of the surface need be specified. Those properties have been quantified in a surface operator and this operator is estimated as part of the multiple removal problem. The surface-related multiple removal algorithm has been formulated in terms of a Neumann series and in terms of an iterative equation. The Neumann formulation requires a nonlinear optimization process for the surface operator; while the iterative formulation needs a number of linear optimizations. The iterative formulation also has the advantage that it can be integrated easily with another multiple removal method. An algorithm for the removal of internal multiples has been proposed as well. This algorithm is an extension of the surface-related method. Removal of internal multiples requires knowledge of the macro velocity model between the surface and the upper boundary of the multiple generating layer. In part II (also published in this issue) the success of the proposed algorithms has been demonstrated on numerical experiments and field data examples.}, author = {Berkhout, A. J. and Verschuur, D. J.}, doi = {10.1190/1.1444261}, journal = {{GEOPHYSICS}}, keywords = {SRME}, url = {http://dx.doi.org/10.1190/1.1444261}, eprint = {http://dx.doi.org/10.1190/1.1444261}, number = {5}, pages = {1586--1595}, publisher = {SEG}, title = {{Estimation of multiple scattering by iterative inversion, Part I: Theoretical considerations}}, volume = {62}, year = {1997} } @inproceedings{Goodfellow2014, title = {{G}enerative {A}dversarial {N}ets}, author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua}, booktitle = {Proceedings of the 27th International Conference on Neural Information Processing Systems}, series = {NIPS'14}, pages={2672--2680}, location = {Montreal, Canada}, year={2014}, url = {http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf}, eprint = {http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf} } @inproceedings{gupta2018deep, title={Random mesh projectors for inverse problems}, author={Konik Kothari and Sidharth Gupta and Maarten v. de Hoop and Ivan Dokmanic}, booktitle={International Conference on Learning Representations}, year={2019}, url={https://openreview.net/forum?id=HyGcghRct7}, eprint = {https://openreview.net/forum?id=HyGcghRct7} } @InProceedings{he2016deep, author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, title = {{D}eep {R}esidual {L}earning for {I}mage {R}ecognition}, DOI = {10.1109/CVPR.2016.90}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2016}, url = {https://ieeexplore.ieee.org/document/7780459}, eprint = {https://ieeexplore.ieee.org/document/7780459}, pages={770--778} } @InProceedings{pix2pix2016, author = {Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A.}, title = {{I}mage-to-{I}mage {T}ranslation with {C}onditional {A}dversarial {N}etworks}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, DOI = {10.1109/CVPR.2017.632}, url = {https://ieeexplore.ieee.org/document/8100115}, eprint = {https://ieeexplore.ieee.org/document/8100115}, month = {July}, year = {2017}, pages={5967--5976} } @InProceedings{johnson2016perceptual, author={Johnson, Justin and Alahi, Alexandre and Fei-Fei, Li}, title={{P}erceptual {L}osses for {R}eal-{T}ime {S}tyle {T}ransfer and {S}uper-{R}esolution}, booktitle={Computer Vision -- European Conference on Computer Vision (ECCV) 2016}, year={2016}, publisher={Springer International Publishing}, pages={694--711}, DOI={10.1007/978-3-319-46475-6_43}, url = {https://link.springer.com/chapter/10.1007%2F978-3-319-46475-6_43}, eprint = {https://link.springer.com/chapter/10.1007%2F978-3-319-46475-6_43}, abstract={We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing perceptual loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results.}, } @article{kingma2015adam, title={{A}dam: {A} {M}ethod for {S}tochastic {O}ptimization}, author={Diederik P. Kingma and Jimmy Ba}, journal={CoRR}, year={2014}, archivePrefix = {arXiv}, arxivId = {1412.6980}, eprint = {1412.6980}, volume={abs/1412.6980} } @article{devito-compiler, author = { {Luporini}, F. and {Lange}, M. and {Louboutin}, M. and {Kukreja}, N. and {H{\"u}ckelheim}, J. and {Yount}, C. and {Witte}, P. and {Kelly}, P.~H.~J. and {Gorman}, G.~J. and {Herrmann}, F.~J. }, title = { Architecture and performance of Devito, a system for automated stencil computation }, journal = { CoRR }, volume = { abs/1807.03032 }, month = { jul }, year = { 2018 }, url = { http://arxiv.org/abs/1807.03032 }, archivePrefix = { arXiv }, eprint = { 1807.03032 } } @article{devito-api, author = { {Louboutin}, M. and {Lange}, M. and {Luporini}, F. and {Kukreja}, N. and {Witte}, P.~A. and {Herrmann}, F.~J. and {Velesko}, P. and {Gorman}, G.~J. }, title = {Devito: an embedded domain-specific language for finite differences and geophysical exploration}, journal = { CoRR }, volume = { abs/1808.01995 }, month = { Aug }, year = { 2018 }, url = { https://arxiv.org/abs/1808.01995 }, archivePrefix = { arXiv }, eprint = { 1808.01995 } } @article{lu2015separated, title={Separated-wavefield imaging using primary and multiple energy}, volume={34}, doi={10.1190/tle34070770.1}, url={http://dx.doi.org/10.1190/tle34070770.1}, eprint={http://dx.doi.org/10.1190/tle34070770.1}, number={7}, journal={The Leading Edge}, author={Lu, Shaoping and Whitmore, Dan N. and Valenciano, Alejandro A. and Chemingui, Nizar}, year={2015}, publisher={Society of Exploration Geophysicists}, pages={770--778} } @article{mandelli2018, author = { Sara Mandelli and Federico Borra and Vincenzo Lipari and Paolo Bestagini and Augusto Sarti and Stefano Tubaro }, title = {Seismic data interpolation through convolutional autoencoder}, journal = {SEG Technical Program Expanded Abstracts 2018}, chapter = {}, pages = {4101--4105}, year = {2018}, doi = {10.1190/segam2018-2995428.1}, URL = {https://library.seg.org/doi/abs/10.1190/segam2018-2995428.1}, eprint = {https://library.seg.org/doi/pdf/10.1190/segam2018-2995428.1} } @article{mikhailiuk2018deep, title={{D}eep {L}earning {A}pplied to {S}eismic {D}ata {I}nterpolation}, doi={10.3997/2214-4609.201800918}, url = {http://www.earthdoc.org/publication/publicationdetails/?publication=92298}, journal={80th EAGE Conference and Exhibition 2018}, author={Mikhailiuk, A. and Faul, A.}, year={2018}, month={Nov} } @article{mosser2018stochastic, title={{S}tochastic {S}eismic {W}aveform {I}nversion {U}sing {G}enerative {A}dversarial {N}etworks {A}s {A} {G}eological {P}rior}, DOI={10.3997/2214-4609.201803018}, url = {http://www.earthdoc.org/publication/publicationdetails/?publication=95011}, journal={First EAGE/PESGB Workshop Machine Learning}, author={Mosser, L. and Dubrule, O. and Blunt, M.}, year={2018}, month={Nov} } @article{ovcharenko2018, title={{L}ow-{F}requency {D}ata {E}xtrapolation {U}sing a {F}eed-{F}orward {ANN}}, DOI={10.3997/2214-4609.201801231}, url = {http://www.earthdoc.org/publication/publicationdetails/?publication=92618}, journal={80th EAGE Conference and Exhibition 2018}, author={Ovcharenko, O. and Kazei, V. and Peter, D. and Zhang, X. and Alkhalifah, T.}, year={2018} } @article{pathak2016context, title={{C}ontext {E}ncoders: {F}eature {L}earning by {I}npainting}, DOI={10.1109/cvpr.2016.278}, url = {https://ieeexplore.ieee.org/document/7780647}, eprint = {https://ieeexplore.ieee.org/document/7780647}, journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, author={Pathak, Deepak and Krahenbuhl, Philipp and Donahue, Jeff and Darrell, Trevor and Efros, Alexei A.}, pages={2536--2544}, year={2016} } @article{richardson2018generative, title={{G}enerative {A}dversarial {N}etworks for {M}odel {O}rder {R}eduction in {S}eismic {F}ull-{W}aveform {I}nversion}, author={Richardson, Alan}, archivePrefix = { arXiv }, arxivId = {1806.00828}, eprint = {1806.00828}, volume = { abs/1806.00828 }, keywords = {preprint}, journal={arXiv}, month = { Jun }, year = { 2018 }, url = { https://arxiv.org/abs/1806.00828 }, eprint = { 1806.00828 } } @article{siahkoohi2018seismic, title={{S}eismic {D}ata {R}econstruction with {G}enerative {A}dversarial {N}etworks}, DOI={10.3997/2214-4609.201801393}, url = {http://www.earthdoc.org/publication/publicationdetails/?publication=92782}, journal={80th EAGE Conference and Exhibition 2018}, author={Siahkoohi, A. and Kumar, R. and Herrmann, F.}, year={2018}, month={Nov} } @article{siahkoohi2018deep, author = {Ali Siahkoohi and Mathias Louboutin and Rajiv Kumar and Felix J. Herrmann}, title = {Deep-convolutional neural networks in prestack seismic: Two exploratory examples}, journal = {SEG Technical Program Expanded Abstracts 2018}, chapter = {}, pages = {2196--2200}, year = {2018}, doi = {10.1190/segam2018-2998599.1}, URL = {https://library.seg.org/doi/abs/10.1190/segam2018-2998599.1}, eprint = {https://library.seg.org/doi/pdf/10.1190/segam2018-2998599.1} } @article{sun2018low, author = {Hongyu Sun and Laurent Demanet}, title = {Low-frequency extrapolation with deep learning}, journal = {SEG Technical Program Expanded Abstracts 2018}, chapter = {}, pages = {2011--2015}, year = {2018}, doi = {10.1190/segam2018-2997928.1}, URL = {https://library.seg.org/doi/abs/10.1190/segam2018-2997928.1}, eprint = {https://library.seg.org/doi/pdf/10.1190/segam2018-2997928.1} } @inproceedings{szegedy2017inception, title={{I}nception-v4, {I}nception-{R}es{N}et and the {I}mpact of {R}esidual {C}onnections on {L}earning.}, author={Szegedy, Christian and Ioffe, Sergey and Vanhoucke, Vincent and Alemi, Alexander A}, booktitle={Proceedings of the Thirty-First Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI-17)}, volume={4}, pages={4278--4284}, year={2017}, crossref = {DBLP:conf/aaai/2017}, url = {http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14806}, } @article{tu2015fast, title={Fast least-squares imaging with surface-related multiples: Application to a North Sea data set}, volume={34}, doi={10.1190/tle34070788.1}, url={http://dx.doi.org/10.1190/tle34070788.1}, eprint={http://dx.doi.org/10.1190/tle34070788.1}, number={7}, journal={The Leading Edge}, publisher={Society of Exploration Geophysicists}, author={Tu, Ning and Herrmann, Felix J.}, year={2015}, pages={788--794} } @article{veillard2018, title={{F}ast {3D} {S}eismic {I}nterpretation with {U}nsupervised {D}eep {L}earning: {A}pplication to a {P}otash {N}etwork in the {N}orth {S}ea}, DOI={10.3997/2214-4609.201800738}, journal={80th EAGE Conference and Exhibition 2018}, author={Veillard, A. and Morère, O. and Grout, M. and Gruffeille, J.}, year={2018} } @article{Verschuur1992, title={Adaptive surface-related multiple elimination}, author={Verschuur, Dirk J and Berkhout, AJ and Wapenaar, CPA}, journal={{GEOPHYSICS}}, volume={57}, number={9}, pages={1166--1177}, year={1992}, publisher={Society of Exploration Geophysicists}, doi = {10.1190/1.1443330}, url = {http://dx.doi.org/10.1190/1.1443330}, eprint = {http://dx.doi.org/10.1190/1.1443330} } @article{verschuur97eom, abstract = {A surface-related multiple-elimination method can be formulated as an iterative procedure: the output of one iteration step is used as input for the next iteration step (part I of this paper). In this paper (part II) it is shown that the procedure can be made very efficient if a good initial estimate of the multiple-free data set can be provided in the first iteration, and in many situations, the Radon-based multiple-elimination method may provide such an estimate. It is also shown that for each iteration, the inverse source wavelet can be accurately estimated by a linear (least-squares) inversion process. Optionally, source and detector variations and directivity effects can be included, although the examples are given without these options. The iterative multiple elimination process, together with the source wavelet estimation, are illustrated with numerical experiments as well as with field data examples. The results show that the surface-related multiple-elimination process is very effective in time gates where the moveout properties of primaries and multiples are very similar (generally deep data), as well as for situations with a complex multiple-generating system.}, author = {Verschuur, D. J. and Berkhout, A. J.}, doi = {10.1190/1.1444262}, url = {http://dx.doi.org/10.1190/1.1444262}, eprint = {http://dx.doi.org/10.1190/1.1444262}, journal = {{GEOPHYSICS}}, keywords = {SRME}, number = {5}, pages = {1596--1611}, publisher = {SEG}, title = {{Estimation of multiple scattering by iterative inversion, Part II: Practical aspects and examples}}, volume = {62}, year = {1997} } @article{wang2018seismic, title={{S}eismic {D}ata {I}nterpolation {U}sing {D}eep {L}earning {B}ased {R}esidual {N}etworks}, DOI={10.3997/2214-4609.201801394}, url = {http://www.earthdoc.org/publication/publicationdetails/?publication=92783}, journal={80th EAGE Conference and Exhibition 2018}, author={Wang, B.f. and Zhang, N. and Lu, W.k. and Zhang, P. and Geng, J.h.}, year={2018}, month={Nov} } @InProceedings{wang2018pix2pixHD, author = {Wang, Ting-Chun and Liu, Ming-Yu and Zhu, Jun-Yan and Tao, Andrew and Kautz, Jan and Catanzaro, Bryan}, title = {{H}igh-{R}esolution {I}mage {S}ynthesis and {S}emantic {M}anipulation with {C}onditional {GAN}s}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, pages = {8798--8807}, doi = {10.1109/CVPR.2018.00917}, url = {https://ieeexplore.ieee.org/document/8579015}, eprint = {https://ieeexplore.ieee.org/document/8579015}, year = {2018} } @article{yang2016time, author = {Mengmeng Yang and Philipp Witte and Zhilong Fang and Felix Herrmann}, title = {Time-domain sparsity-promoting least-squares migration with source estimation}, journal = {SEG Technical Program Expanded Abstracts 2016}, chapter = {}, pages = {4225-4229}, year = {2016}, doi = {10.1190/segam2016-13850609.1}, URL = {https://library.seg.org/doi/abs/10.1190/segam2016-13850609.1}, eprint = {https://library.seg.org/doi/pdf/10.1190/segam2016-13850609.1} } @inproceedings{yosinski2014transferable, author = {Yosinski, Jason and Clune, Jeff and Bengio, Yoshua and Lipson, Hod}, title = {How Transferable Are Features in Deep Neural Networks?}, booktitle = {Proceedings of the 27th International Conference on Neural Information Processing Systems}, series = {NIPS'14}, year = {2014}, location = {Montreal, Canada}, pages = {3320--3328}, numpages = {9}, url = {http://dl.acm.org/citation.cfm?id=2969033.2969197}, } @article{CycleGAN2017, title={{U}npaired {I}mage-to-{I}mage {T}ranslation {U}sing {C}ycle-{C}onsistent {A}dversarial {N}etworks}, DOI={10.1109/iccv.2017.244}, url = {https://ieeexplore.ieee.org/document/8237506}, eprint = {https://ieeexplore.ieee.org/document/8237506}, journal={2017 IEEE International Conference on Computer Vision (ICCV)}, author={Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A.}, year={2017}, pages = {2242--2251} } @misc{tensorflow2015, title={ {TensorFlow}: {L}arge-{S}cale {M}achine {L}earning on {H}eterogeneous {S}ystems}, url={https://www.tensorflow.org/}, note={Software available from tensorflow.org}, author={Abadi, Mart{\'\i}n and Barham, Paul and Chen, Jianmin and Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and Isard, Michael and others}, year={2015}, } @article{doi:10.1190/geo2018-0281.1, author = {Lasse Amundsen and Ørjan Pedersen}, title = {Elimination of temporal dispersion from the finite-difference solutions of wave equations in elastic and anelastic models}, journal = {GEOPHYSICS}, volume = {84}, number = {2}, pages = {T47-T58}, year = {2019}, doi = {10.1190/geo2018-0281.1}, URL = {https://doi.org/10.1190/geo2018-0281.1}, eprint = {https://doi.org/10.1190/geo2018-0281.1}, abstract = {Time integration of wave equations can be carried out with explicit time stepping using a finite-difference (FD) approximation. The wave equation is the partial differential equation that governs the wavefield that is solved for. The FD approximation gives another partial differential equation — the one solved in the computer for the FD wavefield. This approximation to time integration in numerical modeling produces a wavefield contaminated with temporal dispersion, particularly at high frequencies. We find how the Fourier transform can be used to relate the two partial differential equations and their solutions. Each of the two wavefields is then a time-frequency transformation of the other. First, this transformation allows temporal dispersion to be eliminated from the FD wavefield, and second, it allows temporal dispersion to be added to the exact wavefield. The two transforms are band-limited inverse operations. The transforms can be implemented by using time-step independent, noncausal time-varying digital filters that can be precomputed exactly from sums over Bessel functions. Their product becomes the symmetric Toeplitz matrix with the elements defined through the cardinal sine (sinc) function. For anelastic materials, the effect of numerical time dispersion in a wavefield propagating in a medium needs special treatment. Dispersion can be removed by using the time-frequency transform when the FD wavefield is modeled in a medium with the frequency-modified modulus relative to the physical modulus of interest. In the rheological model of the generalized Maxwell body, the frequency-modified modulus is written as a power series, which allows a term-by-term Fourier transform to the time domain. In a low-frequency approximation, the modified modulus obtains the same form as the physical modulus, and it can be implemented as changes in the unrelaxed modulus and shifts of the relaxation frequencies and their strengths of the physical modulus. } }