VALSE 论文速览 第202期：Learning to Manipulate Artistic Images

论文题目：

Learning to Manipulate Artistic Images

作者列表：

郭炜、张瑜琦、马德、郑乾

B站观看网址：

https://www.bilibili.com/video/BV1fSxNeNEcC/?spm_id_from=333.999.0.0&vd_source=2044ac986b5caa4c8b5f00b525441df3

复制链接到浏览器打开或点击阅读原文即可跳转至观看页面。

论文摘要：

Recent advancement in computer vision has significantly lowered the barriers to artistic creation. Exemplar-based image translation methods have attracted much attention due to flexibility and controllability. However, these methods hold assumptions regarding semantics or require semantic information as the input, while accurate semantics is not easy to obtain in artistic images. Besides, these methods suffer from cross-domain artifacts due to training data prior and generate imprecise structure due to feature compression in the spatial domain. In this paper, we propose an arbitrary Style Image Manipulation Network (SIM-Net), which leverages semantic-free information as guidance and a region transportation strategy in a self-supervised manner for image generation. Our method balances computational efficiency and high resolution to a certain extent. Moreover, our method facilitates zero-shot style image manipulation. Both qualitative and quantitative experiments demonstrate the superiority of our method over state-of-the-art methods.

参考文献：

[1] Guo W, Zhang Y, Ma D, et al. Learning to Manipulate Artistic Images[J]. arXiv preprint arXiv:2401.13976, 2024.

论文链接：

[https://arxiv.org/abs/2401.13976]

代码链接：

[https://github.com/SnailForce/SIM-Net]

视频讲者简介：

Wei Guo is currently a second-year Ph.D. at the College of Computer Science, Zhejiang University. He obtained his bachelor's and master's degrees from Northwestern Polytechnical University in 2019 and 2022, respectively. His research interests span multiple directions in computer vision, primarily including image detection and image generation. He is currently focused on learning from 2D vision and textual data and applying it to tasks in 3D vision. He has completed an internship at ByteDance.

特别鸣谢本次论文速览主要组织者：

月度轮值AC：于茜 (北京航空航天大学)