CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models

• URL: http://arxiv.org/abs/2507.13984v1
• Date: Fri, 18 Jul 2025 14:45:48 GMT
• Title: CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models
• Abstract summary: Disentangling content and style from a single image, known as content-style decomposition, enables recontextualization of extracted content and stylization of extracted styles.<n>Visual Autoregressive Modeling has emerged as a promising alternative with a next-scale prediction paradigm.
• Score: 5.821094777538556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Disentangling content and style from a single image, known as content-style decomposition (CSD), enables recontextualization of extracted content and stylization of extracted styles, offering greater creative flexibility in visual synthesis. While recent personalization methods have explored the decomposition of explicit content style, they remain tailored for diffusion models. Meanwhile, Visual Autoregressive Modeling (VAR) has emerged as a promising alternative with a next-scale prediction paradigm, achieving performance comparable to that of diffusion models. In this paper, we explore VAR as a generative framework for CSD, leveraging its scale-wise generation process for improved disentanglement. To this end, we propose CSD-VAR, a novel method that introduces three key innovations: (1) a scale-aware alternating optimization strategy that aligns content and style representation with their respective scales to enhance separation, (2) an SVD-based rectification method to mitigate content leakage into style representations, and (3) an Augmented Key-Value (K-V) memory enhancing content identity preservation. To benchmark this task, we introduce CSD-100, a dataset specifically designed for content-style decomposition, featuring diverse subjects rendered in various artistic styles. Experiments demonstrate that CSD-VAR outperforms prior approaches, achieving superior content preservation and stylization fidelity.

Related papers

• CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models [69.9266117908314]
  Visual autoregressive ( VAR) models have emerged as efficient paradigm for text-to-image generation.<n>Existing VAR-based personalization methods fail to accommodate evolving user demands.<n>We present the first systematic study of continual personalized generation in VAR models.
  arXiv  Detail & Related papers  (2026-05-19T12:18:15Z)
• StyleVAR: Controllable Image Style Transfer via Visual Autoregressive Modeling [0.0]
  We formulate style transfer as conditional discrete sequence modeling in a learned latent space.<n>We introduce a blended cross-attention mechanism in which the evolving target representation attends to its own history.<n>Style VAR consistently outperforms an AdaIN baseline on Style Loss, Content Loss, LPIPS, SSIM, DreamSim, and CLIP similarity.
  arXiv  Detail & Related papers  (2026-04-22T19:52:35Z)
• SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer [0.9558392439655014]
  SCAdapter is a novel technique to separate and integrate content and style features.<n>Our key innovation systematically extracts pure content from content images and style elements from style references, ensuring authentic transfers.
  arXiv  Detail & Related papers  (2025-12-15T04:02:14Z)
• Expanding the Content-Style Frontier: a Balanced Subspace Blending Approach for Content-Style LoRA Fusion [0.0]
  We propose a novel approach to expand the content-style frontier by leveraging Content-Style Subspace Blending and a Content-Style Balance loss.<n>Our method improves content similarity across varying style intensities, significantly broadening the content-style frontier.
  arXiv  Detail & Related papers  (2025-11-03T09:03:45Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning [17.75580298339048]
  We present U.S.O, a Unified Style-Subject Optimized customization model.<n>First, we construct a large-scale triplet dataset consisting of content images, style images, and their corresponding stylized content images.<n>Second, we introduce a disentangled learning scheme that simultaneously aligns style features and disentangles content from style.<n>Third, we incorporate a style reward-learning paradigm denoted as SRL to further enhance the model's performance.
  arXiv  Detail & Related papers  (2025-08-26T12:10:24Z)
• DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition [69.10628479553709]
  We introduce DRC, a novel personalized image generation framework that enhances Large Multimodal Models (LMMs)<n> DRC explicitly extracts user style preferences and semantic intentions from history images and the reference image, respectively.<n>It involves two critical learning stages: 1) Disentanglement learning, which employs a dual-tower disentangler to explicitly separate style and semantic features, optimized via a reconstruction-driven paradigm with difficulty-aware importance sampling; and 2) Personalized modeling, which applies semantic-preserving augmentations to effectively adapt the disentangled representations for robust personalized generation.
  arXiv  Detail & Related papers  (2025-04-24T08:10:10Z)
• AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models [4.364797586362505]
  AttenST is a training-free attention-driven style transfer framework.<n>We propose a style-guided self-attention mechanism that conditions self-attention on the reference style.<n>We also introduce a dual-feature cross-attention mechanism to fuse content and style features.
  arXiv  Detail & Related papers  (2025-03-10T13:28:36Z)
• 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)
• ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model [73.95608242322949]
  Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. We present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion to address challenges such as misinterpreted styles and inconsistent semantics.
  arXiv  Detail & Related papers  (2024-05-24T07:19:40Z)
• HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models [84.12784265734238]
  The goal of Arbitrary Style Transfer (AST) is injecting the artistic features of a style reference into a given image/video. We propose HiCAST, which is capable of explicitly customizing the stylization results according to various source of semantic clues. A novel learning objective is leveraged for video diffusion model training, which significantly improve cross-frame temporal consistency.
  arXiv  Detail & Related papers  (2024-01-11T12:26:23Z)
• CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts [11.752632557524969]
  We propose contrastive learning with data augmentation to disentangle content features from the original representations.<n>Our experiments across diverse datasets demonstrate significant improvements in zero-shot and few-shot classification tasks.
  arXiv  Detail & Related papers  (2023-11-28T03:00:59Z)
• Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations [61.132408427908175]
  zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain. With only a single representative text feature instead of real images, the synthesized images gradually lose diversity. We propose a novel method to find semantic variations of the target text in the CLIP space.
  arXiv  Detail & Related papers  (2023-08-21T08:12:28Z)
• StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval [119.03470556503942]
  Crossmodal matching problem is typically solved by learning a joint embedding space where semantic content shared between photo and sketch modalities are preserved. An effective model needs to explicitly account for this style diversity, crucially, to unseen user styles. Our model can not only disentangle the cross-modal shared semantic content, but can adapt the disentanglement to any unseen user style as well, making the model truly agnostic.
  arXiv  Detail & Related papers  (2021-03-29T15:44:19Z)

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.