CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors 事件

CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors arXiv:2606.05652v1 Announce Type: new Abstract: Unsupervised conditional image generation (UCGen) aims to control generation without relying on manually annotated labels, yet remains challenging due to unstructured semantic representations across granularities. To address this, we propose a novel coarse-to-fine UCGen framework (CoFi-UCGen) that explicitly disentangles global semantics from fine-grained variation