Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
- URL: http://arxiv.org/abs/2411.19231v1
- Date: Thu, 28 Nov 2024 15:56:17 GMT
- Title: Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
- Authors: Yingying Deng, Xiangyu He, Fan Tang, Weiming Dong,
- Abstract summary: Style transfer presents a significant challenge, primarily centered on identifying an appropriate style representation.
In contrast to existing approaches, we have discovered that latent features in vanilla diffusion models inherently contain natural style and content distributions.
Our method adopts dual denoising paths to represent content and style references in latent space, subsequently guiding the content image denoising process with style latent codes.
- Score: 24.88532732093652
- License:
- Abstract: Style transfer presents a significant challenge, primarily centered on identifying an appropriate style representation. Conventional methods employ style loss, derived from second-order statistics or contrastive learning, to constrain style representation in the stylized result. However, these pre-defined style representations often limit stylistic expression, leading to artifacts. In contrast to existing approaches, we have discovered that latent features in vanilla diffusion models inherently contain natural style and content distributions. This allows for direct extraction of style information and seamless integration of generative priors into the content image without necessitating retraining. Our method adopts dual denoising paths to represent content and style references in latent space, subsequently guiding the content image denoising process with style latent codes. We introduce a Cross-attention Reweighting module that utilizes local content features to query style image information best suited to the input patch, thereby aligning the style distribution of the stylized results with that of the style image. Furthermore, we design a scaled adaptive instance normalization to mitigate inconsistencies in color distribution between style and stylized images on a global scale. Through theoretical analysis and extensive experimentation, we demonstrate the effectiveness and superiority of our diffusion-based \uline{z}ero-shot \uline{s}tyle \uline{t}ransfer via \uline{a}djusting style dist\uline{r}ibution, termed Z-STAR+.
Related papers
- DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer [13.588643982359413]
Style transfer aims to fuse the artistic representation of a style image with the structural information of a content image.
Existing methods train specific networks or utilize pre-trained models to learn content and style features.
We propose a novel and training-free approach for style transfer, combining textual embedding with spatial features.
arXiv Detail & Related papers (2024-10-19T06:42:43Z) - ZePo: Zero-Shot Portrait Stylization with Faster Sampling [61.14140480095604]
This paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps.
We propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control.
arXiv Detail & Related papers (2024-08-10T08:53:41Z) - Portrait Diffusion: Training-free Face Stylization with
Chain-of-Painting [64.43760427752532]
Face stylization refers to the transformation of a face into a specific portrait style.
Current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models.
This paper proposes a training-free face stylization framework, named Portrait Diffusion.
arXiv Detail & Related papers (2023-12-03T06:48:35Z) - $Z^*$: Zero-shot Style Transfer via Attention Rearrangement [27.185432348397693]
This study shows that vanilla diffusion models can directly extract style information and seamlessly integrate the generative prior into the content image without retraining.
We adopt dual denoising paths to represent content/style references in latent space and then guide the content image denoising process with style latent codes.
arXiv Detail & Related papers (2023-11-25T11:03:43Z) - A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive
Learning [84.8813842101747]
Unified Contrastive Arbitrary Style Transfer (UCAST) is a novel style representation learning and transfer framework.
We present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature.
Our framework consists of three key components, i.e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer.
arXiv Detail & Related papers (2023-03-09T04:35:00Z) - DiffStyler: Controllable Dual Diffusion for Text-Driven Image
Stylization [66.42741426640633]
DiffStyler is a dual diffusion processing architecture to control the balance between the content and style of diffused results.
We propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image.
arXiv Detail & Related papers (2022-11-19T12:30:44Z) - Learning Graph Neural Networks for Image Style Transfer [131.73237185888215]
State-of-the-art parametric and non-parametric style transfer approaches are prone to either distorted local style patterns due to global statistics alignment, or unpleasing artifacts resulting from patch mismatching.
In this paper, we study a novel semi-parametric neural style transfer framework that alleviates the deficiency of both parametric and non-parametric stylization.
arXiv Detail & Related papers (2022-07-24T07:41:31Z) - Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning [84.8813842101747]
Contrastive Arbitrary Style Transfer (CAST) is a new style representation learning and style transfer method via contrastive learning.
Our framework consists of three key components, i.e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer.
arXiv Detail & Related papers (2022-05-19T13:11:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.