paper-with-me

Papers

Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation

2022-03-24 · CVPR 2022 1 · Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang

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. Project page: \ulr{https://jcyang98.github.io/InST/home.html}. Code available at: \url{https://github.com/jcyang98/InST}.

📄 PDF Abstract BibTeX arXiv:2203.12835

Code (1)

jcyang98/inst 공식 구현 pytorch

Tasks

Style Transfer

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dilated Causal Convolution A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by…
SNAIL The Simple Neural Attention Meta-Learner, or SNAIL, combines the benefits of temporal convolutions and attention to solve meta-learning tasks. They introduce positional…

Similar Papers 제목 키워드 기반

GIST: Towards Photorealistic Style Transfer via Multiscale Geometric Representations

2024-12-03 · Renan A. Rojas-Gomez, Minh N. Do

State-of-the-art Style Transfer methods often leverage pre-trained encoders optimized for discriminative tasks, which may not be ideal for image synthesis. This can result in significant artifacts and loss of photorealis…

Image GenerationStyle Transfer

Enhancing Industrial Transfer Learning with Style Filter: Cost Reduction and Defect-Focus

2024-03-25 · Chen Li, Ruijie Ma, Xiang Qian, Xiaohao Wang 외

Addressing the challenge of data scarcity in industrial domains, transfer learning emerges as a pivotal paradigm. This work introduces Style Filter, a tailored methodology for industrial contexts. By selectively filterin…

Transfer Learning

Geometry Transfer for Stylizing Radiance Fields

2024-02-01 · CVPR 2024 1 · Hyunyoung Jung, Seonghyeon Nam, Nikolaos Sarafianos, Sungjoo Yoo 외

Shape and geometric patterns are essential in defining stylistic identity. However, current 3D style transfer methods predominantly focus on transferring colors and textures, often overlooking geometric aspects. In this …

Style Transfer

Scaling Painting Style Transfer

2022-12-27 · Bruno Galerne, Lara Raad, José Lezama, Jean-Michel Morel

Neural style transfer (NST) is a deep learning technique that produces an unprecedentedly rich style transfer from a style image to a content image. It is particularly impressive when it comes to transferring style from …

global-optimizationGPUStyle Transfer

Geometric Style Transfer

2020-07-10 · Xiao-Chang Liu, Xuan-Yi Li, Ming-Ming Cheng, Peter Hall

Neural style transfer (NST), where an input image is rendered in the style of another image, has been a topic of considerable progress in recent years. Research over that time has been dominated by transferring aspects o…

Style Transfer