PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Image-to-Image Translation

388 평가 기록 62 datasets

Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.

<span style="color:grey; opacity: 0.6">( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )</span>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
DCF
mIoU: 77.7
논문 코드
DCF
MIoU (13 classes): 75.9MIoU (16 classes): 69.3
논문 코드
HRDA + PiPa
mIoU (13 classes): 74.8
논문 코드
MIC
mIoU: 75.9
논문 코드
DP-SIMS (ConvNext-L)
mIoU: 76.3FID: 38.2
논문 -
DP-SIMS (ConvNext-L)
mIoU: 54.3FID: 22.7
논문 -
DP-SIMS (ConvNext-XL)
FID: 13.3
논문 -
VTGAN
FID: 17.3Kernel Inception Distance: 0.00053
논문 코드
DP-GAN
mIoU: 40.4FID: 45.8
논문 코드
IXI
ResViT
PSNR: 35.71 ± 1.77
논문 코드
UniGAN
SSIM: 0.5366KL: 2.6PSNR: 22.8223SD: 19.8276
논문 코드
StarGAN v2
FID: 13.73LPIPS: 0.428
논문 코드

데이터셋

62개
GTAV-to-Cityscapes LabelsSYNTHIA-to-CityscapesSYNTHIA-to-CityscapesGTAV-to-Cityscapes LabelsCityscapes Labels-to-PhotoADE20K Labels-to-PhotosCOCO-Stuff Labels-to-PhotosFundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic PatientsADE20K-Outdoor Labels-to-PhotosIXIcvusaCelebA-HQ

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/2023-MindSpore-4/Code11/tree/main/SPADE 1 논문
github.com/AhmedAmraniAkdi/BdgetNvidiaGaugan 1 논문
github.com/AhmedAmraniAkdi/BudgetNvidiaGaugan 1 논문
github.com/AhmedAmraniAkdi/SmallNvidiaGaugan 1 논문
github.com/alibaba/EasyNLP/tree/master/examples/text2image_generation 1 논문
github.com/boschresearch/OASIS 1 논문
github.com/code-implementation1/Code8/tree/main/SPADE 1 논문
github.com/Cold-Winter/BachGAN 1 논문

하위 태스크

ST Synthetic-to-Real Translation 4 데이터셋 · 119 rows CI Cross-View Image-to-Image Translation 8 데이터셋 · 33 rows MU Multimodal Unsupervised Image-To-Image Translation 6 데이터셋 · 22 rows FT Fundus to Angiography Generation 1 데이터셋 · 9 rows UI Unsupervised Image-To-Image Translation 2 데이터셋 · 7 rows FM Facial Makeup Transfer 2 데이터셋 · 2 rows VT Virtual Try-Off 1 데이터셋 · 1 rows BV Bird View Synthesis 0 데이터셋 · 0 rows IR Image-to-Image Regression 0 데이터셋 · 0 rows PT Photo-To-Caricature Translation 0 데이터셋 · 0 rows RT Real-to-Cartoon translation 0 데이터셋 · 0 rows