Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Models

arXiv:2404.17735v1 Announce Type: new
Abstract: Diffusion probabilistic models (DPMs) have become the state-of-the-art in high-quality image generation. However, DPMs have an arbitrary noisy latent space with no interpretable or controllable semantics. Although there has been significant research effort to improve image sample quality, there is little work on representation-controlled generation using diffusion models. Specifically, causal modeling and controllable counterfactual generation using DPMs is an underexplored area. In this work, we propose CausalDiffAE, a diffusion-based causal representation learning framework to enable …

abstract art arxiv autoencoders become causal counterfactual cs.ai cs.lg diffusion however image image generation quality representation research sample semantics space state type via work