Fabric image outpainting can expand small-sized images to generate visually consistent and texture-continuous images for virtual fitting systems. Colored spun yarn fabrics have periodic textures formed by the organizational structure in the weaving process, and random textures formed by the random mixing of fiber colors. Based on the characteristics of colored spun yarn fabrics, this study proposes a novel image outpainting method based on the U-Net architecture with fast Fourier convolution (FFC). The main novelties of the proposed method include: (1) the integration of fast Fourier convolution (FFC) with residual blocks to effectively capture the global periodic textures inherent in fabrics; (2) a novel temporal spatial predictor (TSP) module to model the spatiotemporal evolution of fabric patterns; and (3) a dedicated multitask loss function that ensures texture consistency and visual realism. A dataset of colored spun yarn fabrics is built as the benchmark to evaluate the proposed framework. Experimental results demonstrate that the proposed method is feasible and effective for image outpainting for colored spun yarn fabrics, being superior to the existing methods. The proposed method can be applied to virtual prototyping and e-commerce applications in the textile industry.
ZhaoXFanKShiX, et al. Virtual fit evaluation of pants using the adaptive network fuzzy inference system. Text Res J2021; 91: 2786-2794. DOI: 10.1177/00405175211020515.
2.
YanNMeiYXuL, et al. Deep learning on image stitching with multi-viewpoint images: A survey. Neural Process Lett2023; 55: 3863-3898. DOI: 10.1007/s11063-023-11226-z.
3.
HuangYHuangJLiuY, et al. Diffusion model-based image editing: A survey. IEEE Trans Pattern Anal Mach Intell2025; 47: 4409-4437. DOI: 10.1109/TPAMI.2025.3541625.
4.
WangZYangZ.Review on image-stitching techniques. Multimedia Syst2020; 26: 413-430. DOI: 10.1007/s00530-020-00651-y.
5.
BrownMLoweDG.Automatic panoramic image stitching using invariant features. Int J Comput Vis2006; 74: 59-73. DOI: 10.1007/s11263-006-0002-3.
6.
ChenYZhengHMaY, et al. Image stitching based on angle-consistent warping. Pattern Recognition2021; 117. DOI: 10.1016/j.patcog.2021.107993.
7.
PacotMPMarcosN.Adaptive feature weighting-based image registration for natural image stitching. Signal Image Video Process2025; 19. DOI: 10.1007/s11760-025-04247-9.
8.
RonnebergerOFischerPBroxT. U-Net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI2015, 2015, pp. 234-241.
9.
ZhangNXiangJWangJ, et al. Appearance generation for colored spun yarn fabric based on conditional image-to-image translation. Color Res Appl2022; 47: 1023-1034. DOI: 10.1002/col.22771.
10.
SabiniMRusakG.Painting outside the box: Image outpainting with GANs. arXiv preprint arXiv:180808483 2018.
11.
ZhouYZhuZBaiX, et al. Non-stationary texture synthesis by adversarial expansion. ACM Trans Graph2018; 37: 1-13. DOI: 10.1145/3197517.3201285.
12.
ZhangXChenFWangC, et al. SiENet: Siamese expansion network for image extrapolation. IEEE Signal Process Lett2020; 27: 1590-1594. DOI: 10.1109/lsp.2020.3019705.
13.
ZhangLWangJShiJ.Multimodal image outpainting with regularized normalized diversification. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2020, pp. 3433-3442.
14.
WangYWeiYQianX, et al. Sketch-guided scenery image outpainting. IEEE Trans Image Process2021; 30: 2643-2655. DOI: 10.1109/tip.2021.3054477.
15.
GaoPYangXZhangR, et al. Generalized image outpainting with U-transformer. Neural Netw2023; 162: 1-10. DOI: 10.1016/j.neunet.2023.02.021.
16.
ZhangZWengHZhangT, et al. A broad generative network for two-stage image outpainting. IEEE Trans Neural Netw Learn Syst2024; 35: 12731-12745. DOI: 10.1109/tnnls.2023.3264617.
17.
WeiGGuoJKeY, et al. A three-stage GAN model based on edge and color prediction for image outpainting. Expert Syst Appl2023; 214. DOI: 10.1016/j.eswa.2022.119136.
YangYYaoSLiuC, et al. Cascaded refinement residual attention network for image outpainting. Multimedia Syst2024; 30. DOI: 10.1007/s00530-024-01265-4.
20.
ZhangZChenCLPWengH, et al. Self-prompt guided image outpainting model for captions absence in social scenes. IEEE Trans Comput Soc Syst2025: 1-12. DOI: 10.1109/TCSS.2025.3547421.
21.
LiXZhengY. Inpaint-outpaint synergy: Mask refinement for trimap-free matting. IEEE Trans Circuits Syst Video Technol2025: 1-1. DOI: 10.1109/TCSVT.2025.3585899.
22.
ZhangSZhouQWangZ, et al. EasyOutPainter: One step image outpainting with both continuous multiple and resolution. IEEE Trans Pattern Anal Mach Intell2025. DOI: 10.1109/TPAMI.2025.3586824.
23.
ZhangNHuQWangL, et al. Appearance change for colored spun yarn fabric based on image color transfer. Text Res J2021; 91: 1439-1451. DOI: 10.1177/0040517520984093.
24.
LinZZhangXZhangN, et al. A novel retrieval strategy for colored spun yarn fabrics based on hand-crafted features and support vector machine. J Text Inst2024; 115: 2535-2544. DOI: 10.1080/00405000.2023.2297475.
25.
GaoPYangXZhangR, et al. Continuous image outpainting with neural ODE. ACM Trans Multimedia Comput Commun Appl2024; 20: 1-16. DOI: 10.1145/3648367.
26.
WangMWangJZhangN, et al. Fabric image retrieval based on decoupling of texture and color feature. J Eng Fiber Fabr2024; 19. DOI: 10.1177/15589250241246074.
27.
ZhangNXiangJWangL, et al. Image retrieval of wool fabric. Part III: based on aggregated convolutional descriptors and approximate nearest neighbors search. Text Res J2021; 92: 434-445. DOI: 10.1177/00405175211037186.
28.
ChiLJiangBMuY.Fast Fourier convolution. In: 34th Conference on Neural Information Processing Systems, 2020, pp. 4479-4488.
29.
TulinBSalihCTZekiÇ, et al. Recognition of leaf diseases in hazelnut orchards with drone imagery by deep learning models: Effectiveness of U-Net model variants. In: 6th International Conference on Computer Systems and Technologies, 2025.
30.
XiangJZhangNPanR, et al. Fabric retrieval based on multi-task learning. IEEE Trans Image Process2021; 30: 1570-1582. DOI: 10.1109/tip.2020.3043877.
31.
KendallAGalYCipollaR. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7482-7491.
32.
CuiGLuoMRiggB, et al. Grading textile fastness. Part 4 An inter-laboratory trial using DigiEye systems. Color Technol2004; 120: 231-235.
