Texture Synthesis Using Convolutional Neural Networks With Long-Range Consistency and Spectral Constraints

被引：0

作者：

Schreiber, Shaun ^{[1
]}

Geldenhuys, Jaco ^{[1
]}

de Villiers, Hendrik ^{[2
]}

机构：

[1] Stellenbosch Univ, Div Comp Sci, Stellenbosch, South Africa

[2] Wageningen UR, Food & Biobased Res, Wageningen, Netherlands

来源：

2016 PATTERN RECOGNITION ASSOCIATION OF SOUTH AFRICA AND ROBOTICS AND MECHATRONICS INTERNATIONAL CONFERENCE (PRASA-ROBMECH) | 2016年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Procedural texture generation enables the creation of more rich and detailed virtual environments without the help of an artist. However, finding a flexible generative model of real world textures remains an open problem. We present a novel Convolutional Neural Network based texture model consisting of two summary statistics (the Gramian and Translation Gramian matrices), as well as spectral constraints. We investigate the Fourier Transform or Window Fourier Transform in applying spectral constraints, and find that the Window Fourier Transform improved the quality of the generated textures. We demonstrate the efficacy of our system by comparing generated output with that of related state of the art systems.

引用

页数：6

共 50 条

[41] Automatic Placenta Abnormality Detection Using Convolutional Neural Networks on Ultrasound Texture
Hu, Zoe
Hu, Ricky
Yan, Ryan
Mayer, Chantal
Rohling, Robert N.
Singla, Rohit
UNCERTAINTY FOR SAFE UTILIZATION OF MACHINE LEARNING IN MEDICAL IMAGING, AND PERINATAL IMAGING, PLACENTAL AND PRETERM IMAGE ANALYSIS, 2021, 12959 : 147 - 156
[42] Robust multimaterial decomposition of spectral CT using convolutional neural networks
Chen, Zhengyang
Li, Liang
OPTICAL ENGINEERING, 2019, 58 (01)
[43] Opportunistic use of spectral holes in Karachi using convolutional neural networks
Shaikh A.Z.
Naqvi S.
Ali M.
Iqbal Y.
Rahim A.
Khadim S.
Altaf T.
1600, Science and Information Organization : 776 - 780
[44] Epileptic Seizure Detection using Spectral Transformation and Convolutional Neural Networks
Cleatus T.S.
Thungamani M.
Journal of The Institution of Engineers (India): Series B, 2022, 103 (04) : 1115 - 1125
[45] Verification system based on long-range iris and Graph Siamese Neural Networks
Zola, Francesco
Fernandez-Carrasco, Jose Alvaro
Lukas Bruse, Jan
Galar, Mikel
Geradts, Zeno
PROCEEDINGS OF 2022 THE 3RD EUROPEAN SYMPOSIUM ON SOFTWARE ENGINEERING, ESSE 2022, 2022, : 80 - 88
[46] Chaff Discrimination Using Convolutional Neural Networks and Range Profile Data
Kaydok, Utku
2020 IEEE INTERNATIONAL RADAR CONFERENCE (RADAR), 2020, : 373 - 377
[47] Shortcut Convolutional Neural Networks for Classification of Gender and Texture
Zhang, Ting
Li, Yujian
Liu, Zhaoying
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, PT II, 2017, 10614 : 30 - 39
[48] Quantitative Ore Texture Analysis with Convolutional Neural Networks
Fu, Y.
Aldrich, C.
IFAC PAPERSONLINE, 2019, 52 (14): : 99 - 104
[49] Texture Adaptive Steganography via Convolutional Neural Networks
Zheng, Chuansheng
Shen, Mengling
Li, Xue M.
Zhang, Xianlin
PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC), 2017, : 1416 - 1420
[50] Deep convolutional neural networks for regular texture recognition
Liu, Ni
Rogers, Mitchell
Cui, Hua
Liu, Weiyu
Li, Xizhi
Delmas, Patrice
PEERJ COMPUTER SCIENCE, 2022, 8

← 1 2 3 4 5 →