paper-with-me

홈 › Papers

Style Transfer by Rigid Alignment in Neural Net Feature Space

2019-09-27 · Suryabhan Singh Hada, Miguel Á. Carreira-Perpiñán

Arbitrary style transfer is an important problem in computer vision that aims to transfer style patterns from an arbitrary style image to a given content image. However, current methods either rely on slow iterative optimization or fast pre-determined feature transformation, but at the cost of compromised visual quality of the styled image; especially, distorted content structure. In this work, we present an effective and efficient approach for arbitrary style transfer that seamlessly transfers style patterns as well as keep content structure intact in the styled image. We achieve this by aligning style features to content features using rigid alignment; thus modifying style features, unlike the existing methods that do the opposite. We demonstrate the effectiveness of the proposed approach by generating high-quality stylized images and compare the results with the current state-of-the-art techniques for arbitrary style transfer.

📄 PDF Abstract BibTeX arXiv:1909.13690

Code (1)

ManthanBhala/Style-Transfer-by-Rigid-Alignment pytorch

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References

2026-03-11 · Boyu He, Yunfan Ye, Chang Liu, Weishang Wu 외 arxiv

Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics, causing uncontrollable stylization; 2) …

Style Transfer

EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer

2018-11-26 · Zhijie Wu, Chunjin Song, Yang Zhou, Minglun Gong 외

Style transfer has been an important topic both in computer vision and graphics. Since the seminal work of Gatys et al. first demonstrates the power of stylization through optimization in the deep feature space, quite a …

Style Transfer

Spatially-Invariant Style-Codes Controlled Makeup Transfer

2021-06-19 · CVPR 2021 1 · Han Deng, Chu Han, Hongmin Cai, Guoqiang Han 외

Transferring makeup from the misaligned reference image is challenging. Previous methods overcome this barrier by computing pixel-wise correspondences between two images, which is inaccurate and computational-expensi…

Decoder

Uncorrelated Feature Encoding for Faster Image Style Transfer

2018-07-04 · Minseong Kim, Jongju Shin, Myung-Cheol Roh, Hyun-Chul Choi

Recent fast style transfer methods use a pre-trained convolutional neural network as a feature encoder and a perceptual loss network. Although the pre-trained network is used to generate responses of receptive fields eff…

image-classificationImage ClassificationStyle Transfer

Advancing Cross-Organ Domain Generalization with Test-Time Style Transfer and Diversity Enhancement

2025-03-24 · Biwen Meng, Xi Long, Wanrong Yang, Ruochen Liu 외

Deep learning has made significant progress in addressing challenges in various fields including computational pathology (CPath). However, due to the complexity of the domain shift problem, the performance of existing mo…

Data AugmentationDiversityDomain GeneralizationStyle Transfer