Diffusion Counterfactual Generation with Semantic Abduction
Journal:
arXiv
Published Date:
Jun 9, 2025
Abstract
Counterfactual image generation presents significant challenges, including
preserving identity, maintaining perceptual quality, and ensuring faithfulness
to an underlying causal model. While existing auto-encoding frameworks admit
semantic latent spaces which can be manipulated for causal control, they
struggle with scalability and fidelity. Advancements in diffusion models
present opportunities for improving counterfactual image editing, having
demonstrated state-of-the-art visual quality, human-aligned perception and
representation learning capabilities. Here, we present a suite of
diffusion-based causal mechanisms, introducing the notions of spatial, semantic
and dynamic abduction. We propose a general framework that integrates semantic
representations into diffusion models through the lens of Pearlian causality to
edit images via a counterfactual reasoning process. To our knowledge, this is
the first work to consider high-level semantic identity preservation for
diffusion counterfactuals and to demonstrate how semantic control enables
principled trade-offs between faithful causal control and identity
preservation.
