paper-with-me

홈 › Papers

Line Search-Based Feature Transformation for Fast, Stable, and Tunable Content-Style Control in Photorealistic Style Transfer

2022-10-12 · Tai-Yin Chiu, Danna Gurari

Photorealistic style transfer is the task of synthesizing a realistic-looking image when adapting the content from one image to appear in the style of another image. Modern models commonly embed a transformation that fuses features describing the content image and style image and then decodes the resulting feature into a stylized image. We introduce a general-purpose transformation that enables controlling the balance between how much content is preserved and the strength of the infused style. We offer the first experiments that demonstrate the performance of existing transformations across different style transfer models and demonstrate how our transformation performs better in its ability to simultaneously run fast, produce consistently reasonable results, and control the balance between content and style in different models. To support reproducing our method and models, we share the code at https://github.com/chiutaiyin/LS-FT.

📄 PDF Abstract BibTeX arXiv:2210.05996

Code (0)

등록된 구현이 없습니다.

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Parameter-Free Style Projection for Arbitrary Style Transfer

2020-03-17 · Siyu Huang, Haoyi Xiong, Tianyang Wang, Bihan Wen 외

Arbitrary image style transfer is a challenging task which aims to stylize a content image conditioned on arbitrary style images. In this task the feature-level content-style transformation plays a vital role for proper …

Style Transfer

Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation

2026-02-13 · Xinyuan Wang, Kunpeng Liu, Arun Vignesh Malarkkan, Yanjie Fu arxiv

Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the l…

Reinforcement Learning

SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning

2022-10-04 · Tanguy Marchand, Boris Muzellec, Constance Beguier, Jean Ogier du Terrail 외

The Yeo-Johnson (YJ) transformation is a standard parametrized per-feature unidimensional transformation often used to Gaussianize features in machine learning. In this paper, we investigate the problem of applying the Y…

Federated Learning

Iterative Feature Transformation for Fast and Versatile Universal Style Transfer

2020-08-01 · ECCV 2020 8 · Tai-Yin Chiu, Danna Gurari

The general framework for fast universal style transfer consists of an autoencoder and a feature transformation at the bottleneck. We propose a new transformation that iteratively stylizes features with analytical gradie…

Style Transfer

Region Feature Descriptor Adapted to High Affine Transformations

2024-02-15 · Shaojie Zhang, Yinghui Wang, Bin Nan, Wei Li 외

To address the issue of feature descriptors being ineffective in representing grayscale feature information when images undergo high affine transformations, leading to a rapid decline in feature matching accuracy, this p…