paper-with-me

Papers

SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective

2023-03-16 · Zipeng Xu, Songlong Xing, Enver Sangineto, Nicu Sebe

Owing to the power of vision-language foundation models, e.g., CLIP, the area of image synthesis has seen recent important advances. Particularly, for style transfer, CLIP enables transferring more general and abstract styles without collecting the style images in advance, as the style can be efficiently described with natural language, and the result is optimized by minimizing the CLIP similarity between the text description and the stylized image. However, directly using CLIP to guide style transfer leads to undesirable artifacts (mainly written words and unrelated visual entities) spread over the image. In this paper, we propose SpectralCLIP, which is based on a spectral representation of the CLIP embedding sequence, where most of the common artifacts occupy specific frequencies. By masking the band including these frequencies, we can condition the generation process to adhere to the target style properties (e.g., color, texture, paint stroke, etc.) while excluding the generation of larger-scale structures corresponding to the artifacts. Experimental results show that SpectralCLIP prevents the generation of artifacts effectively in quantitative and qualitative terms, without impairing the stylisation quality. We also apply SpectralCLIP to text-conditioned image generation and show that it prevents written words in the generated images. Our code is available at https://github.com/zipengxuc/SpectralCLIP.

📄 PDF Abstract BibTeX arXiv:2303.09270

Code (1)

zipengxuc/spectralclip 공식 구현 pytorch

Tasks

Image GenerationStyle Transfer

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Multimodality-guided Image Style Transfer using Cross-modal GAN Inversion

2023-12-04 · Hanyu Wang, Pengxiang Wu, Kevin Dela Rosa, Chen Wang 외

Image Style Transfer (IST) is an interdisciplinary topic of computer vision and art that continuously attracts researchers' interests. Different from traditional Image-guided Image Style Transfer (IIST) methods that requ…

Style Transfer

Image Referenced Sketch Colorization Based on Animation Creation Workflow

2025-02-27 · CVPR 2025 1 · Dingkun Yan, Xinrui Wang, Zhuoru Li, Suguru Saito 외

Sketch colorization plays an important role in animation and digital illustration production tasks. However, existing methods still meet problems in that text-guided methods fail to provide accurate color and style refer…

ColorizationSketch Colorization

MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Reference

2024-09-09 · Jiancheng Huang, Yu Gao, Zequn Jie, Yujie Zhong 외

In this paper, we introduce MRStyle, a comprehensive framework that enables color style transfer using multi-modality reference, including image and text. To achieve a unified style feature space for both modalities, we …

Style Transfer

MAST: Mask-Guided Attention Mass Allocation for Training-Free Multi-Style Transfer

2026-04-14 · Dongkyung Kang, Jaeyeon Hwang, Junseo Park, Minji Kang 외 arxiv

Style transfer aims to render a content image with the visual characteristics of a reference style while preserving its underlying semantic layout and structural geometry. While recent diffusion-based models demonstrate …

Style Transfer

GLEAN: Generative Learning for Eliminating Adversarial Noise

2024-09-15 · Justin Lyu Kim, Kyoungwan Woo

In the age of powerful diffusion models such as DALL-E and Stable Diffusion, many in the digital art community have suffered style mimicry attacks due to fine-tuning these models on their works. The ability to mimic an a…