Multiscale Texture Synthesis and Colourization of Greyscale Textures

被引:0
|
作者
Hast, Anders [1 ]
Ericsson, Martin [2 ]
Seipel, Stefan [3 ]
机构
[1] Univ Gavle, Creat Media Lab, Kungsbacksvagen 47, SE-80176 Gavle, Sweden
[2] Uppsala Univ, UPPMAX, SE-75105 Uppsala, Sweden
[3] Univ Gavle, GraphiX Ctr, SE-80176 Gavle, Sweden
关键词
Multiscale Texture Synthesis; Colorization; Colour transfer; Greyscale Photos;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The main idea presented herein is to use a multiscale texture synthesis approach in order to both colourize and upscale greyscale textures. Such textures can be vintage photos to be used in archaeological or urban 3D visualizations and obviously the colour needs to be reconstructed some way. Due to limited quality, walls etc in such 3D visualizations will appear either pixelized or blurry when the viewer approaches them on a close distance. The latter if some kind of interpolation technique is being used to reduce the pixelization. The low resolution greyscale texture and a high resolution coloured texture is used for the colourization and upscaling, which will produce a colour version of the greyscale texture with 4 times higher resolution in each upscale step. The novel idea is to use multiscale texture synthesis in HSV space for the first upscale in order to create a RGB colour image for subsequent upscaling, using either ordinary RGB multiscale texture synthesis or continue using HSV multiscale texture synthesis. These two main approaches will be compared and discussed.
引用
收藏
页码:55 / +
页数:2
相关论文
共 50 条
  • [31] Evaluation of protein crystallization states based on texture information derived from greyscale images
    Saitoh, K
    Kawabata, K
    Asama, H
    Mishima, T
    Sugahara, M
    Miyano, M
    ACTA CRYSTALLOGRAPHICA SECTION D-STRUCTURAL BIOLOGY, 2005, 61 : 873 - 880
  • [32] Invariant texture perception is harder with synthetic textures: Implications for models of texture processing
    Balas, Benjamin
    Conlin, Catherine
    VISION RESEARCH, 2015, 115 : 271 - 279
  • [33] Detecting main frequencies for multiscale texture image and texture segmenting
    Cai, Ye-Jing
    Yi, Jin-Ping
    Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences, 2002, 29 (03):
  • [34] An approach for multiscale analysis of visual texture
    Lizarraga-Morales, Rocio A.
    Sanchez-Yanez, Raul E.
    Ayala-Ramirez, Victor
    2009 III CONFERENCE OF UNIVERSITY OF GUANAJUATO IEEE STUDENTS CHAPTER (IEEEXPO 2009), 2009, : 12 - 15
  • [35] Texture synthesis-by-analysis method based on a multiscale early-vision model
    Portilla, J
    Navarro, R
    Nestares, O
    Tabernero, A
    OPTICAL ENGINEERING, 1996, 35 (08) : 2403 - 2417
  • [36] Multiscale asymmetry signatures for texture analysis
    Van de Wouwer, G
    Weyn, B
    Van Dyck, D
    ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5, 2004, : 1517 - 1520
  • [37] Sharpness for Texture Retrieval in Multiscale Domain
    Zhang, Jiuwen
    Yang, Chao
    Yu, Zhiquan
    2013 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 2013, : 378 - 381
  • [38] A variational model for multiscale texture extraction
    Tang, Liming
    He, Chuanjiang
    OPTIK, 2016, 127 (01): : 299 - 309
  • [39] Multiscale Analysis for Improving Texture Classification
    Ataky, Steve Tsham Mpinda
    Saqui, Diego
    de Matos, Jonathan
    de Souza Britto Junior, Alceu
    Lameiras Koerich, Alessandro
    APPLIED SCIENCES-BASEL, 2023, 13 (03):
  • [40] EMPIRICAL TEXTURE CORRECTIONS FOR ASYMMETRIC DIFFRACTION AND INCLINED TEXTURES
    CERNY, R
    VALVODA, V
    CHLADEK, M
    JOURNAL OF APPLIED CRYSTALLOGRAPHY, 1995, 28 (pt 3) : 247 - 253