.png){kind=icon}
返回
Learning generalizable visual representations with causal diffusion model for controllable editing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113162.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• A diffusion model-based causal representation learning method, CausalDiffuser, is proposed. • The representations are divided into causal and stochastic representations to ensure the image reconstruction quality. • Structural causal model serves as priors, capturing the causal relationships among the underlying generative factors (i.e., visual attributes). • A composite loss is designed to enhance the causal representation learning capability by introducing supervisory information. • The effectiveness of CausalDiffuser is validated on synthetic and real-world datasets.
Keyword:
causal representation learning
diffusion model
structural causal model
controllable editing
generalizable visual representations
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
FastEdit: fast text-guided single-image editing via semantic-aware diffusion fine-tuningFastEdit：基于语义感知扩散微调的快速文本引导单图像编辑.png)
Pattern Recognition
OAAI
Pattern RecognitionIF7.6
OAAI分享收藏Blessing few-shot segmentation via semi-supervised learning with noisy support imagesPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏HybridEditDif: Text and exemplar guided image editing with diffusion modelsHybridEditDif：基于扩散模型的文本和示例引导图像编辑Pattern Recognition
Pattern RecognitionIF7.6
PREAI
分享收藏 没有更多内容
没有更多内容