paper-with-me

Image-to-Image Translation 벤치마크

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

45개 결과 · ⬇ CSV · JSON

FID 낮을수록 좋음

13.3 37.85 62.4 86.95 111.5 2017-07 2026-09 CRN — 70.4 (2017-07-28) CRN — 70.4 (2017-07-28) CRN — 70.4 (2017-07-28) pix2pixHD — 111.5 (2017-11-30) pix2pixHD — 111.5 (2017-11-30) pix2pixHD — 111.5 (2017-11-30) SPADE — 22.6 (2019-03-18) SPADE — 22.6 (2019-03-18) SPADE — 22.6 (2019-03-18) CC-FPSE — 19.2 (2019-10-15) CC-FPSE — 19.2 (2019-10-15) CC-FPSE — 19.2 (2019-10-15) CC-FPSE-AUG — 19.1 (2020-11-25) Pix2PixHD-AUG — 54.2 (2020-11-25) CC-FPSE-AUG — 19.1 (2020-11-25) Pix2PixHD-AUG — 54.2 (2020-11-25) CC-FPSE-AUG — 19.1 (2020-11-25) Pix2PixHD-AUG — 54.2 (2020-11-25) OASIS — 17.0 (2020-12-08) OASIS — 17.0 (2020-12-08) OASIS — 17.0 (2020-12-08) VQGAN+Transformer — 22.4 (2020-12-17) VQGAN+Transformer — 22.4 (2020-12-17) VQGAN+Transformer — 22.4 (2020-12-17) USIS — 27.8 (2021-09-29) USIS — 27.8 (2021-09-29) USIS — 27.8 (2021-09-29) PoE-GAN — 15.8 (2021-12-09) PoE-GAN — 15.8 (2021-12-09) PoE-GAN — 15.8 (2021-12-09) PITI — 15.6 (2022-05-25) PITI — 15.6 (2022-05-25) PITI — 15.6 (2022-05-25) USIS-Wavelet — 28.6 (2023-05-16) USIS-Wavelet — 28.6 (2023-05-16) USIS-Wavelet — 28.6 (2023-05-16) DP-SIMS (ConvNext-XL) — 13.3 (2023-12-20) DP-SIMS (ConvNext-L) — 13.6 (2023-12-20) DP-SIMS (ConvNext-XL) — 13.3 (2023-12-20) DP-SIMS (ConvNext-L) — 13.6 (2023-12-20) DP-SIMS (ConvNext-XL) — 13.3 (2023-12-20) DP-SIMS (ConvNext-L) — 13.6 (2023-12-20) SCDM — 15.3 (2024-02-26) SCDM — 15.3 (2024-02-26) SCDM — 15.3 (2024-02-26) CRN — 70.4 (2017-07-28) SPADE — 22.6 (2019-03-18) CC-FPSE — 19.2 (2019-10-15) CC-FPSE-AUG — 19.1 (2020-11-25) OASIS — 17.0 (2020-12-08) PoE-GAN — 15.8 (2021-12-09) PITI — 15.6 (2022-05-25) DP-SIMS (ConvNext-XL) — 13.3 (2023-12-20)
RankModel FIDAccuracymIoULPIPS PaperCodeYear
21 OASIS 17.0–44.1– You Only Need Adversarial Supervision for Semantic Image Synthesis boschresearch/OASIS 2020
22 CC-FPSE-AUG 19.171.542.1– Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis 2020
23 CC-FPSE 19.270.7%41.6– Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis xh-liu/CC-FPSE 2019
24 VQGAN+Transformer 22.4––– Taming Transformers for High-Resolution Image Synthesis CompVis/taming-transformers · alibaba/EasyNLP · dome272/VQGAN · +10 2020
25 SPADE 22.667.9%37.4– Semantic Image Synthesis with Spatially-Adaptive Normalization NVlabs/SPADE · shaoanlu/fewshot-face-translation-GAN · mindslab-ai/hififace · +21 2019
26 USIS 27.8–14.06– USIS: Unsupervised Semantic Image Synthesis GeorgeEskandar/USIS-Unsupervised-Semantic-Image-Synthesis 2021
27 USIS-Wavelet 28.6–13.4– Wavelet-based Unsupervised Label-to-Image Translation GeorgeEskandar/USIS-Unsupervised-Semantic-Image-Synthesis 2023
28 Pix2PixHD-AUG 54.254.121.9– Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis 2020
29 CRN 70.440.4%23.7– Photographic Image Synthesis with Cascaded Refinement Networks 2017
30 pix2pixHD 111.545.8%14.6– High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs NVIDIA/pix2pixHD · mingyuliutw/UNIT · moabarar/nemar · +18 2017
31 DP-SIMS (ConvNext-XL) 13.3––– Unlocking Pre-trained Image Backbones for Semantic Image Synthesis 2023
32 DP-SIMS (ConvNext-L) 13.6––– Unlocking Pre-trained Image Backbones for Semantic Image Synthesis 2023
33 SCDM 15.3–38.10.519 Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis mlvlab/scdm 2024
34 PITI 15.6––– Pretraining is All You Need for Image-to-Image Translation PITI-Synthesis/PITI · rinnakk/japanese-stable-diffusion 2022
35 PoE-GAN 15.8––– Multimodal Conditional Image Synthesis with Product-of-Experts GANs 2021
36 OASIS 17.0–44.1– You Only Need Adversarial Supervision for Semantic Image Synthesis boschresearch/OASIS 2020
37 CC-FPSE-AUG 19.171.542.1– Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis 2020
38 CC-FPSE 19.270.7%41.6– Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis xh-liu/CC-FPSE 2019
39 VQGAN+Transformer 22.4––– Taming Transformers for High-Resolution Image Synthesis CompVis/taming-transformers · alibaba/EasyNLP · dome272/VQGAN · +10 2020
40 SPADE 22.667.9%37.4– Semantic Image Synthesis with Spatially-Adaptive Normalization NVlabs/SPADE · shaoanlu/fewshot-face-translation-GAN · mindslab-ai/hififace · +21 2019
← 이전 21–40 / 45 다음 → 페이지당 10 20 50 100