Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences 事件

Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences arXiv:2605.25759v1 Announce Type: new Abstract: Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through part-specific modules or localized loss weighting during supervised fine-tuning on high-quality human photos, but such datasets are l