CLeaR: A Unified Framework for Resolving the Leakage-Degradation Dilemma in Style Transfer

arXiv:2609.38136 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/0606zt/CLeaR

Terminology

• Alignment — 26× in this paper · explained in 1 episode
• Ensemble Inversion — 23× in this paper
• Calibration — 20× in this paper · explained in 7 episodes
• Diffusion Model — 18× in this paper · explained in 8 episodes
• Energy-Guided Calibration — 14× in this paper
• Diffusion Models — 12× in this paper · explained in 6 episodes
• Orthogonal Subspace Projection — 8× in this paper
• Grounding — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Distillation — 5× in this paper · explained in 2 episodes
• Inverse Problem — 4× in this paper · explained in 2 episodes
• Training-Free Framework — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Embeddings — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Ensemble Learning — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes

Sources

• LeakyCLIP: Extracting Training Data from CLIP
• A Sensitivity Matrix Based Methodology for Inverse Problem Formulation
• A Neural Algorithm of Artistic Style
• StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter
• Nomic Embed Vision: Expanding the Latent Space
• DINOv3
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Measuring Style Similarity in Diffusion Models
• Kimi K2: Open Agentic Intelligence
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
• OmniStyle2: Learning to Stylize by Learning to Destylize
• Qwen3 Technical Report
• IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models