Image-to-Image Translation on COCO-Stuff Labels-to-Photos

Metric: FID (lower is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

#	Model↕	FID▲	Extra Data	Paper	Date↕	Code
1	DP-SIMS (ConvNext-XL)	13.3	No	Unlocking Pre-trained Image Backbones for Semant...	2023-12-20	-
2	DP-SIMS (ConvNext-L)	13.6	No	Unlocking Pre-trained Image Backbones for Semant...	2023-12-20	-
3	SCDM	15.3	No	Stochastic Conditional Diffusion Models for Robu...	2024-02-26	Code
4	PITI	15.6	No	Pretraining is All You Need for Image-to-Image T...	2022-05-25	Code
5	PoE-GAN	15.8	No	Multimodal Conditional Image Synthesis with Prod...	2021-12-09	-
6	OASIS	17	No	You Only Need Adversarial Supervision for Semant...	2020-12-08	Code
7	CC-FPSE-AUG	19.1	No	Improving Augmentation and Evaluation Schemes fo...	2020-11-25	-
8	CC-FPSE	19.2	No	Learning to Predict Layout-to-image Conditional ...	2019-10-15	Code
9	VQGAN+Transformer	22.4	No	Taming Transformers for High-Resolution Image Sy...	2020-12-17	Code
10	SPADE	22.6	No	Semantic Image Synthesis with Spatially-Adaptive...	2019-03-18	Code
11	USIS	27.8	No	USIS: Unsupervised Semantic Image Synthesis	2021-09-29	Code
12	USIS-Wavelet	28.6	No	Wavelet-based Unsupervised Label-to-Image Transl...	2023-05-16	Code
13	Pix2PixHD-AUG	54.2	No	Improving Augmentation and Evaluation Schemes fo...	2020-11-25	-
14	CRN	70.4	No	Photographic Image Synthesis with Cascaded Refin...	2017-07-28	-
15	pix2pixHD	111.5	No	High-Resolution Image Synthesis and Semantic Man...	2017-11-30	Code