Studies Advanced in Image Generation Techniques based on Deep Learning
DOI:
https://doi.org/10.54097/hset.v39i.6646Keywords:
Image Generation Techniques; Generated Models; Deep Learning.Abstract
A popular area of study in computer vision is image generation. How to improve the authenticity and diversity of generated images, and how to reduce the use of hardware resources and the size of model storage to make it more conducive to model landing are the focus and difficulty of image generation algorithms. Moreover, in practical applications, many other tasks are closely related to the image generation task, utilizing the created picture can lower the cost of data collecting, and the produced picture's quality directly influences how well some activities work. This article first introduces the definition of the generated model in supervised learning and unsupervised learning, and analyzes several reasons why learning should be generated into a model. It also introduces the development of the generated models in China and abroad, and makes a simple classification of the generated models with the previous depth degree.
Downloads
References
Ummenhofer B, Zhou H, Uhrig J, et al. Demon: Depth and motion network for learning monocular stereo[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 5038-5047.
Qi X, Liao R, Liu Z, et al. Geonet: Geometric neural network for joint depth and surface normal estimation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 283-291.
Hinton G E, Sejnowski T J. Learning and relearning in Boltzmann machines[J]. Parallel distributed processing: Explorations in the microstructure of cognition, 1986, 1(282-317): 2.
Lu X. Image analysis for face recognition[J]. Personal notes, 2003: 36.
Wang Y, Tan D J, Navab N, et al. Self-supervised Latent Space Optimization with Nebula Variational Coding[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
Vahdat A, Kautz J. NVAE: A deep hierarchical variational autoencoder[J]. Advances in Neural Information Processing Systems, 2020, 33: 19667-19679.
Creswell A, White T, Dumoulin V, et al. Generative adversarial networks: An overview[J]. IEEE signal processing magazine, 2018, 35(1): 53-65.
Gowdy J N, Subramanya A, Bartels C, et al. DBN based multi-stream models for audio-visual speech recognition[C]//2004 IEEE International conference on acoustics, speech, and signal processing. IEEE, 2004, 1: I-993.Zou M, Conzen S D. A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time course microarray data[J]. Bioinformatics, 2005, 21(1): 71-79.
S. Benaim and L. Wolf, “One-sided unsupervised domain mapping,” arXiv preprint arXiv:1706.00826, 2017.
An J, Cho S. Variational autoencoder based anomaly detection using reconstruction probability[J]. Special Lecture on IE, 2015, 2(1): 1-18.7
Qiao T, Zhang J, Xu D, et al. Mirrorgan: Learning text-to-image generation by redescription [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 1505-1514.
J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, “Unpaired image-to-image translation using cycle-consistent adversarial networks,” arXiv preprint arXiv:1703.10593, 2017.
Mao X, Li Q, Xie H, et al. Least squares generative adversarial networks[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2794-2802.
Berthelot D, Schumm T, Metz L. Began: Boundary equilibrium generative adversarial networks[J]. arXiv preprint arXiv:1703.10717, 2017.
Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv preprint arXiv:1511.06434, 2015.
Dai B, Wipf D. Diagnosing and enhancing VAE models[J]. arXiv preprint arXiv:1903.05789, 2019.
Kingma D P, Welling M. Auto-encoding variational bayes[J]. arXiv preprint arXiv:1312.6114, 2013.
Pu Y, Gan Z, Henao R, et al. Variational autoencoder for deep learning of images, labels and captions[J]. Advances in neural information processing systems, 2016, 29.
Higgins I, Matthey L, Pal A, et al. beta-vae: Learning basic visual concepts with a constrained variational framework[J]. 2016.
Liu K, Shuai R, Ma L. Cells image generation method based on VAE-SGAN[J]. Procedia Computer Science, 2021, 183: 589-595.Huang H, Yu P S, Wang C. An introduction to image synthesis with generative adversarial nets[J]. arXiv preprint arXiv:1803.04469, 2018.
Yu F, Seff A, Zhang Y, et al. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop[J]. arXiv preprint arXiv:1506.03365, 2015.
Pu Y, Gan Z, Henao R, et al. Variational autoencoder for deep learning of images, labels and captions[J]. Advances in neural information processing systems, 2016, 29.
Higgins I, Matthey L, Pal A, et al. beta-vae: Learning basic visual concepts with a constrained variational framework[J]. 2016.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
