Industrial Style Transfer With Large-Scale Geometric Warping and Content Preservation

Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 7834-7843

Abstract


We propose a novel style transfer method to quickly create a new visual product with a nice appearance for industrial designers' reference. Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product. Our model, Industrial Style Transfer (InST), consists of large-scale geometric warping (LGW) and interest-consistency texture transfer (ICTT). LGW aims to explore an unsupervised transformation between the shape masks of the source and target products for fitting large-scale shape warping. Furthermore, we introduce a mask smoothness regularization term to prevent the abrupt changes of the details of the source product. ICTT introduces an interest regularization term to maintain important contents of the warped product when it is stylized by using the art style image. Extensive experimental results demonstrate that InST achieves state-of-the-art performance on multiple visual product design tasks, e.g., companies' snail logos and classical bottles (please see Fig. 1). To the best of our knowledge, we are the first to extend the neural style transfer method to create industrial product appearances. Code is available at https://jcyang98.github.io/InST/home.html

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Jinchao and Guo, Fei and Chen, Shuo and Li, Jun and Yang, Jian}, title = {Industrial Style Transfer With Large-Scale Geometric Warping and Content Preservation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {7834-7843} }