Cross-scale Aligned Supervision for Training GANs 事件

Cross-scale Aligned Supervision for Training GANs arXiv:2605.26449v1 Announce Type: new Abstract: Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-fine hierarchical generation. In this work, we challenge this interpretation. We argue that standard scale-wise adversarial supervision does not construct a proper coarse-to-fine hierarchy: each intermediate image is independently pushed toward the rea