.png){kind=icon}
Return
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}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
causal representation learning
diffusion model
structural causal model
controllable editing
generalizable visual representations
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
FastEdit: fast text-guided single-image editing via semantic-aware diffusion fine-tuning.png)
Pattern Recognition
OAAI
Pattern RecognitionIF7.6
OAAIShareSaveBlessing few-shot segmentation via semi-supervised learning with noisy support imagesPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveHybridEditDif: Text and exemplar guided image editing with diffusion modelsPattern Recognition
Pattern RecognitionIF7.6
PREAI
ShareSave no more
no more