TexControl: Sketch-Based Two-Stage Fashion Image Generation Using Diffusion Model

被引:0
|
作者
Zhang, Yongming [1 ]
Zhang, Tianyu [1 ]
Xie, Haoran [1 ]
机构
[1] Japan Adv Inst Sci & Technol, Nomi, Ishikawa, Japan
关键词
Diffusion model; Sketch-based generation; Fashion design;
D O I
10.1109/NICOInt62634.2024.00021
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Deep learning-based sketch-to-clothing image generation provides the initial designs and inspiration in the fashion design processes. However, clothing generation from freehand drawing is challenging due to the sparse and ambiguous information from the drawn sketches. The current generation models may have difficulty generating detailed texture information. In this work, we propose TexControl, a sketch-based fashion generation framework that uses a two-stage pipeline to generate the fashion image corresponding to the sketch input. First, we adopt ControlNet to generate the fashion image from sketch and keep the image outline stable. Then, we use an image-to-image method to optimize the detailed textures of the generated images and obtain the final results. The evaluation results show that TexControl can generate fashion images with high-quality texture as fine-grained image generation.
引用
收藏
页码:64 / 68
页数:5
相关论文
共 50 条
  • [1] DualSmoke: Sketch-based smoke illustration design with two-stage generative model
    Xie, Haoran
    Arihara, Keisuke
    Sato, Syuhei
    Miyata, Kazunori
    [J]. COMPUTATIONAL VISUAL MEDIA, 2024,
  • [2] Sketch-based compatible clothing image generation
    Cao, Xiao-Lu
    Lu, Fu-Nan
    Zhu, Xiang
    Weng, Li-Bo
    Lu, Shu-Fang
    Gao, Fei
    [J]. Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2023, 57 (05): : 939 - 947
  • [3] Sketch-based Image Retrieval using Sketch Tokens
    Wang, Shu
    Miao, Zhenjiang
    [J]. PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, 2015, : 396 - 400
  • [4] Sketch2Tooncity:Sketch-based City Generation Using Neurosymbolic Model
    Kanda, Junya
    He, Yi
    Xie, Haoran
    Miyata, Kazunori
    [J]. INTERNATIONAL WORKSHOP ON ADVANCED IMAGING TECHNOLOGY, IWAIT 2024, 2024, 13164
  • [5] Sketch-based image retrieval using keyshapes
    Jose M. Saavedra
    Benjamin Bustos
    [J]. Multimedia Tools and Applications, 2014, 73 : 2033 - 2062
  • [6] Sketch-based image retrieval using keyshapes
    Saavedra, Jose M.
    Bustos, Benjamin
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2014, 73 (03) : 2033 - 2062
  • [7] Sketch-based Image Retrieval by Using Saliency
    Pan, Da
    Shi, Ping
    Li, Cuiying
    [J]. 2014 11TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD), 2014, : 825 - 829
  • [8] Text to Image Synthesis Using Two-Stage Generation and Two-Stage Discrimination
    Zhang, Zhiqiang
    Zhang, Yunye
    Yu, Wenxin
    He, Gang
    Jiang, Ning
    He, Gang
    Fan, Yibo
    Yang, Zhuo
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2019, PT II, 2019, 11776 : 110 - 114
  • [9] Sketch-based Image Retrieval Using Contour Segments
    Zhang, Yuting
    Qian, Xueming
    Tan, Xianglong
    [J]. 2015 IEEE 17TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2015,
  • [10] Sketch-based image retrieval using angular partitioning
    Chalechale, A
    Naghdy, G
    Mertins, A
    [J]. PROCEEDINGS OF THE 3RD IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2003, : 668 - 671