Mixed-Domain Edge-Aware Image Manipulation

被引:38
|
作者
Li, Xian-Ying [1 ,2 ]
Gu, Yan [1 ,2 ]
Hu, Shi-Min [1 ,2 ]
Martin, Ralph R. [3 ]
机构
[1] Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China
[2] Beijing Engn Res Ctr Intelligent Proc Visual Medi, Beijing 100084, Peoples R China
[3] Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 3AA, S Glam, Wales
基金
英国工程与自然科学研究理事会;
关键词
Edge-aware image processing; mixed-domain; multi-scale method; optimization-based image processing;
D O I
10.1109/TIP.2013.2237922
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a novel approach to edge-aware image manipulation. Our method processes a Gaussian pyramid from coarse to fine, and at each level, applies a nonlinear filter bank to the neighborhood of each pixel. Outputs of these spatially-varying filters are merged using global optimization. The optimization problem is solved using an explicit mixeddomain ( real space and DCT transform space) solution, which is efficient, accurate, and easy-to-implement. We demonstrate applications of our method to a set of problems, including detail and contrast manipulation, HDR compression, nonphotorealistic rendering, and haze removal.
引用
收藏
页码:1915 / 1925
页数:11
相关论文
共 50 条
  • [41] Edge-Aware Point Set Resampling
    Huang, Hui
    Wu, Shihao
    Gong, Minglun
    Cohen-Or, Daniel
    Ascher, Uri
    Zhang, Hao
    ACM TRANSACTIONS ON GRAPHICS, 2013, 32 (01):
  • [42] Edge-Aware Point Cloud Registration
    Gao, Junjie
    Wang, Ruian
    Wang, Zixiong
    Dong, Qiujie
    Gao, Haohao
    Xin, Shiqing
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2024, 36 (07): : 1122 - 1130
  • [43] Edge-Aware Interactive Contrast Enhancement
    Ko, Keunsoo
    Kim, Chang-Su
    IEEE ACCESS, 2022, 10 : 98981 - 98992
  • [44] Depth estimation from single-shot monocular endoscope image using image domain adaptation and edge-aware depth estimation
    Oda, Masahiro
    Itoh, Hayato
    Tanaka, Kiyohito
    Takabatake, Hirotsugu
    Mori, Masaki
    Natori, Hiroshi
    Mori, Kensaku
    COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION, 2022, 10 (03): : 266 - 273
  • [45] Sym-Parameterized Dynamic Inference for Mixed-Domain Image Translation
    Chang, Simyung
    Park, SeongUk
    Yang, John
    Kwak, Nojun
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 4802 - 4810
  • [46] Edge-Aware Level Set Diffusion and Bilateral Filtering Reconstruction for Image Magnification
    黄华
    臧彧
    Paul L.Rosin
    齐春
    JournalofComputerScience&Technology, 2009, 24 (04) : 734 - 744
  • [47] Variational method for joint optical flow estimation and edge-aware image restoration
    Tu, Zhigang
    Xie, Wei
    Cao, Jun
    van Gemeren, Coert
    Poppe, Ronald
    Veltkamp, Remco C.
    PATTERN RECOGNITION, 2017, 65 : 11 - 25
  • [48] EASI-Tex: Edge-Aware Mesh Texturing from Single Image
    Perla, Sai Raj Kishore
    Wang, Yizhi
    Mahdavi-Amiri, Ali
    Zhang, Hao
    ACM TRANSACTIONS ON GRAPHICS, 2024, 43 (04):
  • [49] Differentiable double clustering with edge-aware superpixel fitting for unsupervised image segmentation
    Li, Xin
    Chen, Xiaoying
    Qiu, Yuanbo
    Tao, Chunfeng
    Zheng, Pan
    DISPLAYS, 2024, 83
  • [50] Edge-Aware Image Super-Resolution Using a Generative Adversarial Network
    Das B.
    Roy S.D.
    SN Computer Science, 4 (2)