paper-with-me

AFHQ

Animal Faces-HQ

홈페이지 · 논문 327편

Animal FacesHQ (AFHQ) is a dataset of animal faces consisting of 15,000 high-quality images at 512 × 512 resolution. The dataset includes three domains of cat, dog, and wildlife, each providing 5000 images. By having multiple (three) domains and diverse images of various breeds (≥ eight) per each domain, AFHQ sets a more challenging image-to-image translation problem. All images are vertically and horizontally aligned to have the eyes at the center. The low-quality images were discarded by human effort. Source: StarGAN v2: Diverse Image Synthesis for Multiple Domains

Images

벤치마크

Multimodal Unsupervised Image-To-Image Translation on AFHQ 결과 12개
Image Generation on AFHQ Cat 결과 8개
Image Generation on AFHQV2 결과 7개
Image Generation on AFHQ Dog 결과 6개
Image-to-Image Translation on AFHQ 결과 6개
Image Generation on AFHQ Wild 결과 5개