Home

Awesome

Image-to-Image papers

A collection of image-to-image papers.

Papers are ordered in arXiv first version submitting time (if applicable).

Feel free to send a PR or issue.

TOC

Supervised

NoteModelPaperConferencepaper linkcode link
pix2pixImage-to-Image Translation with Conditional Adversarial NetworksCVPR 20171611.07004junyanz/pytorch-CycleGAN-and-pix2pix
texture guidedTextureGANTextureGAN: Controlling Deep Image Synthesis with Texture PatchesCVPR 20181706.02823janesjanes/Pytorch-TextureGAN
Contextual GANImage Generation from Sketch Constraint Using Contextual GANECCV 20181711.08972
pix2pix-HDHigh-Resolution Image Synthesis and Semantic Manipulation with Conditional GANsCVPR 20181711.11585NVIDIA/pix2pixHD
one-to-manyBicycleGANToward Multimodal Image-to-Image TranslationNIPS 20171711.11586junyanz/BicycleGAN
keypoint guidedG2-GANGeometry Guided Adversarial Facial Expression SynthesisMM 20181712.03474
contour2imSmart, Sparse Contours to Represent and Edit ImagesCVPR 20181712.08232website
disentangleCross-domain disentanglement networksImage-to-image translation for cross-domain disentanglementNIPS 20181805.09730
gestureGestureGANGestureGAN for Hand Gesture-to-Gesture Translation in the WildMM 20181808.04859Ha0Tang/GestureGAN
videovid2vidVideo-to-Video SynthesisNIPS 20181808.06601NVIDIA/vid2vid
videopix2pix-HD + Temporal Smoothing + faceGANEverybody Dance NowECCVW 20181808.07371website
(un)supervisedMSGANMode Seeking Generative Adversarial Networks for Diverse Image SynthesisCVPR 20191903.05628HelenMao/MSGAN
semantic to imageSPADESemantic Image Synthesis with Spatially-Adaptive NormalizationCVPR 20191903.07291NVlabs/SPADE
Edge and color domain to reconstrcut imagePI-RECPI-REC: Progressive Image Reconstruction Network With Edge and Color Domain1903.10146youyuge34/PI-REC
Cross-view image translationSelectionGANMulti-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image TranslationCVPR 20191904.06807Ha0Tang/SelectionGAN
keypoint guidedC2-GANCycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image GenerationMM 20191908.00999
Few shot, videoFew-shot vid2vidFew-shot Video-to-Video SynthesisNeurIPS 20191910.12713NVlabs/few-shot-vid2vid

Unsupervised

Unsupervised - General

NoteModelPaperConferencepaper linkcode link
DTNUnsupervised Cross-Domain Image GenerationICLR 20171611.02200yunjey/domain-transfer-network (unofficial)
UNITUnsupervised image-to-image translation networksNIPS 20171703.00848mingyuliutw/UNIT
DiscoGANLearning to Discover Cross-Domain Relations with Generative Adversarial NetworksICML 20171703.05192SKTBrain/DiscoGAN
CycleGANUnpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksICCV 20171703.10593junyanz/pytorch-CycleGAN-and-pix2pix
DualGANDualGAN: Unsupervised Dual Learning for Image-to-Image TranslationICCV 20171704.02510duxingren14/DualGAN
DistanceGANOne-Sided Unsupervised Domain MappingNIPS 20171706.00826sagiebenaim/DistanceGAN
SisGANSisGAN: Semantic Image Synthesis via Adversarial LearningICCV 20171707.06873woozzu/dong_iccv_2017
semi supervisedTriangle GANTriangle Generative Adversarial NetworksNIPS 20171709.06548LiqunChen0606/Triangle-GAN
CartoonGANCartoonGAN: Generative Adversarial Networks for Photo CartoonizationCVPR 2018thecvfFlyingGoblin/CartoonGAN, unofficial test, unofficial pytorch
non-adversarialNAMNAM: Non-Adversarial Unsupervised Domain MappingECCV 20181806.00804facebookresearch/nam
SCANUnsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial NetworksECCV 20181807.08536
dilated conv, improve shape deform.GANimorphImproved Shape Deformation in Unsupervised Image to Image TranslationECCV 20181808.04325brownvc/ganimorph
videoRecycle-GANRecycle-GAN: Unsupervised Video RetargetingECCV 20181808.05174aayushbansal/Recycle-GAN
OT-CycleGANGuiding the One-to-one Mapping in CycleGAN via Optimal TransportAAAI 20191811.06284
Art2RealArt2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image TranslationCVPR 20191811.10666aimagelab/art2real
latent cross-consistencyCrossNetCrossNet: Latent Cross-Consistency for Unpaired Image TranslationWACV 20201901.04530
HarmonicGANHarmonic Unpaired Image-to-image TranslationICLR 20191902.09727
Person GenerationDG-NetJoint Discriminative and Generative Learning for Person Re-identificationCVPR 20191904.07223NVlabs/DG-Net
TransGaGaTransGaGa: Geometry-Aware Unsupervised Image-to-Image TranslationCVPR 20191904.09571project
AGUITAttribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning1904.12428imlixinyang/AGUIT
few shotFUNITFew-Shot Unsupervised Image-to-Image TranslationICCV 20191905.01723project, nvlabs/FUNIT
zero shotZstGANZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation1906.00184linjx-ustc1106/ZstGAN-PyTorch
Cross-Domain Cascaded Deep Feature Translation1906.01526
Breaking the cycle -- Colleagues are all you need.1911.10538

Unsupervised - Attention/Instance guided

NoteModelPaperConferencepaper linkcode link
maskContrastGANGenerative Semantic Manipulation with Mask-Contrasting GANECCV 20181708.00315
attentionDA-GANDA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial NetworksCVPR 20181802.06454
mask / attentionAttention-GANAttention-GAN for Object Transfiguration in Wild ImagesECCV 20181803.06798
attentionAttention guided GANUnsupervised Attention-guided Image to Image TranslationNIPS 20181806.02311AlamiMejjati/Unsupervised-Attention-guided-Image-to-Image-Translation
attention, one-sidedShow, Attend and Translate: Unsupervised Image Translation with Self-Regularization and AttentionTIP 20191806.06195
instance aware - maskInstaGANInstance-aware image-to-image translationICLR 2019openreviewsangwoomo/instagan
AttentionGANAttention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image TranslationIJCNN 20191903.12296Ha0Tang/AttentionGAN
instance level - bboxINITTowards Instance-level Image-to-Image TranslationCVPR 20191905.01744project
mask guidedMask-Guided Portrait Editing with Conditional GANsCVPR 20191905.10346cientgu/Mask_Guided_Portrait_Editing
U-GAT-ITU-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image TranslationICLR 20201907.10830taki0112/UGATIT, znxlwm/UGATIT-pytorch

Unsupervised - Many-to-many (Attributes)

NoteModelPaperConferencepaper linkcode link
IcGANInvertible Conditional GANs for image editingNIPSW 20161611.06355Guim3/IcGAN
Conditional CycleGANConditional CycleGAN for Attribute Guided Face Image GenerationECCV 20181705.09966
StarGANStarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image TranslationCVPR 20181711.09020yunjey/StarGAN
AttGANAttGAN: Facial Attribute Editing by Only Changing What You WantTIP 20191711.10678LynnHo/AttGAN-Tensorflow
ComboGANComboGAN: Unrestrained Scalability for Image Domain TranslationCVPRW 20181712.06909AAnoosheh/ComboGAN
AugCGAN (Augmented CycleGAN)Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired DataICML 20181802.10151aalmah/augmented_cyclegan
ModularGANModular Generative Adversarial NetworksECCV 20181804.03343
sparsely grouped datasetSG-GANSparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute ManipulationMM 20181805.07509zhangqianhui/Sparsely-Grouped-GAN
GANimationGANimation: Anatomically-aware Facial Animation from a Single ImageECCV 20181807.09251albertpumarola/GANimation
SingleGANSingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial LearningACCV 20181810.04991Xiaoming-Yu/SingleGAN
SMITSMIT: Stochastic Multi-Label Image-to-Image TranslationICCVW 20191812.03704BCV-Uniandes/SMIT
InjectionGANToward Learning a Unified Many-to-Many Mapping for Diverse Image Translation1905.08766
Image-to-Image Translation with Multi-Path Consistency RegularizationIJCAI 20191905.12498
RelGANRelGAN: Multi-Domain Image-to-Image Translation via Relative AttributesICCV 20191908.07269elvisyjlin/RelGAN-PyTorch, willylulu/RelGAN
StarGAN v2StarGAN v2: Diverse Image Synthesis for Multiple DomainsCVPR 20201912.01865clovaai/stargan-v2

Unsupervised - Disentangled (and/or Exemplar guided)

NoteModelPaperConferencepaper linkcode link
XGANXGAN: Unsupervised Image-to-Image Translation for Many-to-Many MappingsICML 20181711.05139dataset
ELEGANTELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face AttributesECCV 20181803.10562Prinsphield/ELEGANT
MUNITMultimodal Unsupervised Image-to-Image TranslationECCV 20181804.04732NVlabs/MUNIT
cd-GAN (Conditional DualGAN)Conditional Image-to-Image TranslationCVPR 20181805.00251
EG-UNITExemplar Guided Unsupervised Image-to-Image TranslationICLR 20191805.11145
PairedCycleGANPairedCycleGAN: Asymmetric Style Transfer for Applying and Removing MakeupCVPR 2018thecvf
DRITDiverse Image-to-Image Translation via Disentangled RepresentationsECCV 20181808.00948HsinYingLee/DRIT
UFDNA Unified Feature Disentangler for Multi-Domain Image Translation and ManipulationNIPS 20181809.01361Alexander-H-Liu/UFDN
non-disentangle, face makeup guidedBeautyGANBeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial NetworkMM 2018authorwtjiang98/BeautyGAN_pytorch
GDWCTImage-to-Image Translation via Group-wise Deep Whitening and Coloring TransformationCVPR 20191812.09912WonwoongCho/GDWCT
DRIT++DRIT++: Diverse Image-to-Image Translation via Disentangled RepresentationsIJCV 20201905.01270project, HsinYingLee/MDMM
HiDTHigh-Resolution Daytime Translation Without Domain LabelsCVPR 20202003.08791project, saic-mdal/HiDT

To be classified