Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang

TL;DR
This paper introduces InST, a neural style transfer method that combines large-scale geometric warping and content preservation to efficiently generate stylized industrial product images, advancing industrial design visualization.
Contribution
It presents a novel neural style transfer framework with large-scale geometric warping and interest-preserving texture transfer, tailored for industrial product design applications.
Findings
Achieves state-of-the-art results on industrial design tasks
Effectively preserves content while applying artistic styles
First to extend neural style transfer to industrial product appearance creation
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Human Motion and Animation · Industrial Vision Systems and Defect Detection
MethodsAttention Is All You Need · Softmax · Dilated Causal Convolution · Simple Neural Attention Meta-Learner
