Imagen de Portada

DICE: Disentangling Artist Style from Content via Contrastive Subspace Decomposition in Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Tong, Zhang, Ru, Liu, Jianyi
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
por: Zhang, Tong, et al.
Publicado: (2025)

CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models
por: Nguyen, Quang-Binh, et al.
Publicado: (2025)

Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis
por: Luo, Yufei, et al.
Publicado: (2024)

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
por: Ma, Pingchuan, et al.
Publicado: (2025)

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
por: Zargarbashi, Fatemeh, et al.
Publicado: (2026)

DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation
por: Varur, Sneha, et al.
Publicado: (2025)

Domain Generalization for Endoscopic Image Segmentation by Disentangling Style-Content Information and SuperPixel Consistency
por: Teevno, Mansoor Ali, et al.
Publicado: (2024)

Sub-DM:Subspace Diffusion Model with Orthogonal Decomposition for MRI Reconstruction
por: Guan, Yu, et al.
Publicado: (2024)

Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
por: Liu, Kaiyuan, et al.
Publicado: (2024)

DisentTalk: Cross-lingual Talking Face Generation via Semantic Disentangled Diffusion Model
por: Liu, Kangwei, et al.
Publicado: (2025)

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
por: Chen, Yiwen, et al.
Publicado: (2024)

AI-Generated Content Enhanced Computer-Aided Diagnosis Model for Thyroid Nodules: A ChatGPT-Style Assistant
por: Yao, Jincao, et al.
Publicado: (2024)

StyleVAR: Controllable Image Style Transfer via Visual Autoregressive Modeling
por: Jing, Liqi, et al.
Publicado: (2026)

StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
por: Li, Yanjie, et al.
Publicado: (2025)

Understanding Sources of Demographic Predictability in Brain MRI via Disentangling Anatomy and Contrast
por: Avci, Mehmet Yigit, et al.
Publicado: (2026)

Subspace Clustering on Incomplete Data with Self-Supervised Contrastive Learning
por: Li, Huanran, et al.
Publicado: (2026)

SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer
por: Trinh, Luan Thanh, et al.
Publicado: (2025)

PathoSyn: Imaging-Pathology MRI Synthesis via Disentangled Deviation Diffusion
por: Wang, Jian, et al.
Publicado: (2025)

Contrastive Learning Guided Latent Diffusion Model for Image-to-Image Translation
por: Si, Qi, et al.
Publicado: (2025)

Distilling Cross-Modal Knowledge via Feature Disentanglement
por: Liu, Junhong, et al.
Publicado: (2025)

Mitigating Hallucinations in Video Large Language Models via Spatiotemporal-Semantic Contrastive Decoding
por: Gao, Yuansheng, et al.
Publicado: (2026)

Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification
por: Dombrowski, Mischa, et al.
Publicado: (2024)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
por: Jun, Youngjun, et al.
Publicado: (2024)

Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
por: Yang, Tao, et al.
Publicado: (2024)

LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing
por: Fu, Wingwa, et al.
Publicado: (2026)

Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation
por: Wang, Hengyi, et al.
Publicado: (2026)

Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
por: Chormai, Pattarawat, et al.
Publicado: (2022)

Long-Text-to-Image Generation via Compositional Prompt Decomposition
por: Huang, Jen-Yuan, et al.
Publicado: (2026)

DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations
por: Avci, Mehmet Yigit, et al.
Publicado: (2025)

Subspace Alignment for Vision-Language Model Test-time Adaptation
por: Zeng, Zhichen, et al.
Publicado: (2026)

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
por: Cai, Peiliang, et al.
Publicado: (2026)

HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models
por: Wang, Hanzhang, et al.
Publicado: (2024)

Interpretable and Sparse Linear Attention with Decoupled Membership-Subspace Modeling via MCR2 Objective
por: Liu, Tianyuan, et al.
Publicado: (2026)

MoST: Motion Style Transformer between Diverse Action Contents
por: Kim, Boeun, et al.
Publicado: (2024)

Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods
por: Cho, Wonwoong, et al.
Publicado: (2023)

Unsupervised Synthetic Image Attribution: Alignment and Disentanglement
por: Liu, Zongfang, et al.
Publicado: (2026)

Can Diffusion Models Disentangle? A Theoretical Perspective
por: Wang, Liming, et al.
Publicado: (2025)

StyleMamba : State Space Model for Efficient Text-driven Image Style Transfer
por: Wang, Zijia, et al.
Publicado: (2024)

ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models
por: Zhang, Jianyi, et al.
Publicado: (2024)

Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
por: Fu, Jinhu, et al.
Publicado: (2026)