HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Pose Transfer On Deep Fashion

평가 지표

IS

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	IS	SSIM	Paper Title	Repository
ADGAN	3.364	0.772	Controllable Person Image Synthesis with Attribute-Decomposed GAN	-
UPGPT	-	-	UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer	-
Disentangled PG	3.228	0.614	Disentangled Person Image Generation	-
PG Squared	3.090	0.762	Pose Guided Person Image Generation	-
Deformable GAN	3.439	0.756	Deformable GANs for Pose-based Human Image Generation	-
DiOr	-	0.806	Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing	-
bFT	3.22	0.767	Guided Image-to-Image Translation with Bi-Directional Feature Transformation	-
Progressive Pose Attention	3.209	0.773	Progressive Pose Attention Transfer for Person Image Generation	-
Leffa	-	-	Learning Flow Fields in Attention for Controllable Person Image Generation	-
RATE	3.125	0.774	Region-adaptive Texture Enhancement for Detailed Person Image Synthesis	-
XingGAN	3.476	0.778	XingGAN for Person Image Generation	-
BiGraphGAN	3.430	0.778	Bipartite Graph Reasoning GANs for Person Image Generation	-

0 of 12 row(s) selected.

Pose Transfer On Deep Fashion | SOTA | HyperAI초신경