We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.

翻译：我们提出了一种通用因果生成建模框架，利用深度结构因果模型实现高保真图像反事实的精确估计。针对高维结构化变量（如图像）的干预查询与反事实查询，其估计仍是一项具有挑战性的任务。我们借鉴因果中介分析的思想与生成建模的最新进展，设计出适用于因果模型中结构化变量的新型深度因果机制。实验结果表明，所提出的机制能够通过反事实的公理正确性度量实现精确的外推计算，以及对直接效应、间接效应与总效应的估计。